system

Abstract

We provide the system. [Solution] A means for the user to input their desired conditions, A means for sending the entered conditions to the server, A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server, A means of providing the generated recipe to the user, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, when a user challenges a new dish, it takes time and effort to search for recipes and combine ingredients, which is particularly difficult for novice cooks. Also, it is laborious to select the optimal recipe from the search results, and it is necessary to screen from a variety of information. Furthermore, if the searched recipe is difficult to understand or the procedure is complicated, the motivation to challenge will be diminished. Under such circumstances, there is a need for a system that can easily and efficiently propose new dishes to users and provide the detailed procedures and precautions necessary for their implementation.

Means for Solving the Problems

[0005] This invention proposes a system in which a user inputs desired conditions, and a server generates and provides a new recipe based on those conditions. This system includes means for the user to input ingredients and desired dish type via a browser or application, means for easily sending the input conditions to the server, means for the server to analyze the received conditions and generate a new recipe using a generative AI, and means for providing the generated recipe to the user. Furthermore, the generated recipe includes a detailed list of ingredients, cooking procedures, and precautions, making it easy for even cooking beginners to try new dishes. This system solves the problems of conventional systems and makes it possible to efficiently and easily suggest new dishes to users.

[0006] A "user" is an individual or group that uses the system to receive suggestions for new cooking recipes.

[0007] "Conditions" refer to information entered by the user, including desired ingredients, type of dish, cooking time, difficulty level, etc.

[0008] "Means" refers to the various functions and elements that constitute a system, and the methods and procedures by which they work together to solve a problem.

[0009] A "server" is a computing system that receives conditions sent by a user, generates new recipes using generative AI, and provides them to the user.

[0010] "Generative AI" is an artificial intelligence technology that automatically generates new cooking recipes based on the conditions it receives.

[0011] A "recipe" is information that shows users the specific steps for making a new dish, and includes a list of ingredients, cooking instructions, and precautions.

[0012] An "ingredients list" is a list of the ingredients needed to make a dish.

[0013] A "cooking procedure" is a set of specific steps that show how to use the ingredients to complete a dish.

[0014] "Points to note" refers to things to pay particular attention to or tips to use when cooking.

[0015] A "browser" is software that allows users to view web pages via the internet.

[0016] An "application" is specialized software that allows a user to utilize a system. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] ---

[0039] This invention is a system that allows users to easily receive suggestions for new cooking recipes, and its implementation follows the steps below.

[0040] First, users access the system using a browser or a dedicated application. Users can enter their desired conditions on the interface. These conditions include the ingredients to be used, cooking time, type of dish, and difficulty level. For example, if a user wants a "simple chicken dish," they would enter the corresponding information. Once the user enters the conditions and clicks the "Request Suggestions" button, the terminal sends the entered conditions to the server.

[0041] The terminal converts the user's input into JSON data and sends it to the server as an HTTP request. The server receives this request and parses the data. Based on this parsed data, the server inputs conditions into a generative AI. The generative AI generates a new recipe based on the received conditions. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[0042] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[0043] material:

[0044] 300g chicken breast

[0045] 1 lemon

[0046] 2 cloves of garlic

[0047] 2 tablespoons olive oil

[0048] Salt and pepper to taste

[0049] Cooking instructions:

[0050] 1. Cut the chicken breast into bite-sized pieces.

[0051] 2. Grate the lemon zest and squeeze out the juice.

[0052] 3. Mince the garlic.

[0053] 4. Heat olive oil in a frying pan and sauté the garlic.

[0054] 5. Add the chicken and sauté until it has a nice golden brown color.

[0055] 6. Add the lemon juice and zest, and season with salt and pepper.

[0056] Points to note:

[0057] Be careful not to burn the garlic.

[0058] To prevent the lemon flavor from dissipating, do not overheat it.

[0059] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays the recipe to the user in an easy-to-read format. This allows the user to start cooking based on the suggested recipe.

[0060] This system allows users to receive new recipe suggestions with just a few clicks, and making them is easy. Users can create new dishes simply by following the provided ingredients and cooking instructions. In this way, the present invention provides a system that allows even cooking beginners to easily expand their culinary repertoire.

[0061] ---

[0062] The following describes the processing flow.

[0063] ---

[0064] Step 1:

[0065] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, if the user wants a "simple chicken dish," they would enter information such as "chicken," "simple," and "grilled."

[0066] Step 2:

[0067] The user enters the conditions and clicks the "Request Proposal" button. The device then converts the user's entered conditions into JSON data. This data includes the entered ingredients, cooking method, difficulty level, etc.

[0068] Step 3:

[0069] The terminal sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill"}.

[0070] Step 4:

[0071] The server receives HTTP requests from terminals and parses the data. Based on the parsed data, the server creates prompts to generate new cooking recipes. These prompts are then input into a generative AI.

[0072] Step 5:

[0073] The server inputs prompts to the generative AI. Based on the received prompts, the generative AI generates a new recipe. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the specified criteria.

[0074] Step 6:

[0075] Generative AI generates recipes based on given conditions. For example, it might generate a dish called "Lemon Garlic Chicken Sauté." This recipe includes the following information:

[0076] material:

[0077] 300g chicken breast

[0078] 1 lemon

[0079] 2 cloves of garlic

[0080] 2 tablespoons olive oil

[0081] Salt and pepper to taste

[0082] Cooking instructions:

[0083] 1. Cut the chicken breast into bite-sized pieces.

[0084] 2. Grate the lemon zest and squeeze out the juice.

[0085] 3. Mince the garlic.

[0086] 4. Heat olive oil in a frying pan and sauté the garlic.

[0087] 5. Add the chicken and sauté until it has a nice golden brown color.

[0088] 6. Add the lemon juice and zest, and season with salt and pepper.

[0089] Points to note:

[0090] Be careful not to burn the garlic.

[0091] To prevent the lemon flavor from dissipating, do not overheat it.

[0092] Step 7:

[0093] The server converts the generated recipe into JSON data and sends it to the terminal as an HTTP response.

[0094] Step 8:

[0095] The terminal analyzes the recipe data received from the server and displays it on the user interface. This allows the user to check the list of ingredients, cooking instructions, and important notes.

[0096] Step 9:

[0097] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking instructions. They complete the dish safely and deliciously, paying attention to all precautions.

[0098] ---

[0099] The above is a detailed explanation of the processing steps of this system.

[0100] (Example 1)

[0101] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Conventional recipe suggestion systems have struggled to generate new recipes that are appropriate and timely in response to user input. Furthermore, the generated recipes sometimes lacked comprehensive ingredient lists, cooking instructions, and important notes, making them difficult for users to use.

[0103] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0104] In this invention, the server includes means for inputting conditions desired by the user, means for transmitting the input conditions to the server, means for the server to parse the received conditions in JSON format and input the parsed data into a generation AI model, means for generating a new cooking recipe based on the conditions using the generation AI model, and means for transmitting the generated recipe to a terminal and displaying the recipe on the terminal. This makes it possible to quickly generate a new cooking recipe based on the conditions desired by the user and provide a recipe that includes a detailed list of ingredients, cooking procedures, and precautions.

[0105] "Means for users to input desired conditions" refers to methods and devices for users to input cooking-related conditions on an interface.

[0106] "Means for sending entered conditions to the server" means a method and device for sending conditions entered from a terminal to a server using a communication protocol (e.g., HTTP).

[0107] "Means for a server to parse the conditions it receives in JSON format and input the parsed data into a generating AI model" means a method and apparatus for a server to parse the conditions it receives in JSON format using a data analysis library and input the analysis results into a generating AI model.

[0108] "Means for generating new recipes based on conditions using a generative AI model" means a method and apparatus for generating new recipes that match user conditions using a generative AI model.

[0109] "Means for sending generated recipes to a terminal and displaying the recipes on the terminal" means a method and apparatus for converting generated recipes into JSON format, sending them from the server to the terminal, and displaying them on the terminal in a format that is easy for the user to view.

[0110] "Means for converting and analyzing conditions in JSON format for input into a generated AI model by the server" means a method and apparatus for converting raw data received by the server into JSON format and analyzing those conditions.

[0111] "The generated recipe includes a list of ingredients, cooking instructions, and notes" means that the recipe output by the generating AI model includes a specific list of ingredients, detailed cooking instructions, and notes to keep in mind while cooking.

[0112] Modes for carrying out the invention

[0113] This invention provides a system that allows users to easily receive suggestions for new cooking recipes, and its implementation involves the following steps.

[0114] First, users access this system using an internet-connected device (such as a PC, smartphone, or tablet). To access the system, users need a web browser (e.g., Chrome, Firefox) or a dedicated application. On this interface, users enter their desired ingredients, cooking time, type of dish, difficulty level, and other preferences. For example, if they want a simple chicken dish, they would enter the corresponding information.

[0115] When a user clicks the "Request Proposal" button, the device converts the entered conditions into JSON data and sends it to the server as an HTTP request. The communication protocol used at this time is HTTP.

[0116] The server receives this request and parses the conditions in JSON format using a data analysis library (e.g., FastAPI, Flask). The parsed data is then input into a generative AI model (e.g., GPT-3®, BERT). The generative AI model generates a new recipe based on the received conditions. This generation process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[0117] The generated recipe is converted back to JSON format on the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays it to the user in an easy-to-understand format. Frontend libraries and frameworks such as JavaScript® and React may be used at this stage.

[0118] For example, if a new dish called "Lemon Garlic Chicken Sauté" is proposed, the generated recipe would look like this:

[0119] material:

[0120] 300g chicken breast

[0121] 1 lemon

[0122] 2 cloves of garlic

[0123] 2 tablespoons olive oil

[0124] Salt and pepper to taste

[0125] Cooking instructions:

[0126] 1. Cut the chicken breast into bite-sized pieces.

[0127] 2. Grate the lemon zest and squeeze out the juice.

[0128] 3. Mince the garlic.

[0129] 4. Heat olive oil in a frying pan and sauté the garlic.

[0130] 5. Add the chicken and sauté until it has a nice golden brown color.

[0131] 6. Add the lemon juice and zest, and season with salt and pepper.

[0132] Points to note:

[0133] Be careful not to burn the garlic.

[0134] To prevent the lemon flavor from dissipating, do not overheat it.

[0135] The advantage of this system is that users can receive new recipe suggestions with just a few clicks, and the process is simple. Users can create new dishes simply by following the suggested ingredients and cooking instructions. In this way, the present invention makes it possible for even cooking beginners to easily expand their culinary repertoire.

[0136] Examples of prompt statements are as follows:

[0137] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[0138] By inputting this prompt into the AI ​​model, a recipe suitable for the given conditions is generated and provided to the user.

[0139] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0140] System program processing flow

[0141] Step 1:

[0142] The user enters their desired conditions. The user inputs the ingredients they want to use, cooking time, type of dish, difficulty level, etc., on the interface. For example, they might select "chicken," "under 30 minutes," "sauté," and "easy." This generates input data based on the user's desired conditions. This input data is saved in JSON format.

[0143] Input: Conditions entered by the user in the interface

[0144] Output: Input data in JSON format

[0145] Step 2:

[0146] The terminal sends the input data to the server. When the user clicks the "Request Proposal" button, the terminal converts the entered conditions into JSON format data and sends it to the server as an HTTP request.

[0147] Input: Input data in JSON format

[0148] Output: HTTP request sent to the server

[0149] Step 3:

[0150] The server analyzes the received conditions. The server analyzes the received JSON data using a data analysis library (e.g., FastAPI, Flask) and inputs the analyzed data into the generating AI model. Specific data analysis steps include schema validation and extraction of necessary items.

[0151] Input: HTTP request in JSON format

[0152] Output: Analyzed data (Example: {"Ingredients": "Chicken", "Cooking time": "Under 30 minutes", "Type of dish": "Sauté", "Difficulty": "Easy"})

[0153] Step 4:

[0154] A generative AI model generates a new recipe. The server inputs the analyzed data as prompts into the generative AI model (e.g., GPT-3). The generative AI model generates a new recipe based on the given conditions. This process includes generating an ingredient list, cooking instructions, and notes.

[0155] Input: Analyzed data

[0156] Output: Generated recipe (Example: {"Ingredients": {...}, "Cooking Instructions": [...], "Notes": [...]})

[0157] Step 5:

[0158] The server converts the generated recipe into JSON format and sends it to the terminal. The generated recipe is then converted back into JSON format within the server and sent to the terminal as an HTTP response. Conversion and validation take place during this process.

[0159] Input: Generated recipe

[0160] Output: HTTP response in JSON format

[0161] Step 6:

[0162] The device parses and displays the recipe. The device reads the received data using a JSON parsing library and displays the recipe to the user in an easy-to-understand format. This display may utilize front-end libraries such as JavaScript or React.

[0163] Input: HTTP response in JSON format

[0164] Output: Recipe display in a format viewable by the user.

[0165] Example prompt statements

[0166] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[0167] By inputting this prompt into the AI ​​model, a recipe suitable for the given conditions is generated and provided to the user.

[0168] (Application Example 1)

[0169] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0170] Conventional recipe suggestion systems only provide users with suggested recipes, leaving them responsible for purchasing and arranging for the delivery of ingredients. Furthermore, there was a lack of systems capable of adequately handling recipe generation based on specific conditions. Additionally, there was insufficient means to efficiently procure the necessary ingredients when generating new recipes.

[0171] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0172] In this invention, the server includes means for inputting desired conditions from the user, means for transmitting the input conditions to the server, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions received by the server, means for ordering the necessary ingredients through a delivery service based on the generated recipe, and means for providing the generated recipe to the user. As a result, the user can not only be offered cooking recipes based on their desired conditions, but also have the delivery of the necessary ingredients for those recipes arranged all at once.

[0173] "A means for users to input their desired conditions" refers to a component that provides an interface where users can input conditions such as the ingredients they want to use, cooking time, type of dish, and difficulty level.

[0174] "Means for sending entered conditions to the server" refers to a data communication function for sending conditions entered by the user to the server via the network.

[0175] "A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server" refers to a function in which the server analyzes the user's conditions and generates new cooking recipes using a generative AI model based on those conditions.

[0176] "A means of ordering necessary ingredients through a delivery service based on a generated recipe" refers to a function that automatically orders the necessary ingredients through an online delivery service based on the ingredient list described in the generated recipe.

[0177] "Means of providing generated recipes to users" refers to a function for displaying or providing generated new cooking recipes to the user's device.

[0178] This invention is a system that proposes new recipes based on the user's desired conditions and allows the user to order the necessary ingredients through a delivery service based on those recipes. This system is configured as follows:

[0179] First, users access the system using a dedicated smartphone application. On the interface, users can input their desired conditions (for example, ingredients to use, cooking time, type of dish, difficulty level, etc.). This allows users to input specific instructions such as "a simple dish using chicken."

[0180] The entered conditions are converted into JSON data and sent to the server as an HTTP request. This communication is implemented using, for example, a frontend built with React Native and a backend using Node.js and Express.

[0181] The server receives the request and analyzes the data. The analyzed data is input as a prompt to the generative AI based on OpenAI's GPT-4 model. An example of a prompt is: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes."

[0182] Generative AI generates new recipes based on the conditions it receives. This generation process includes algorithms to consider ingredients that meet the conditions, cooking procedures, and points to note. For example, if a new dish called "Chicken Stir-fry with Butter and Soy Sauce" is proposed, the generated recipe will include the following details:

[0183] material:

[0184] 200g chicken breast

[0185] 30g butter

[0186] 2 tablespoons soy sauce

[0187] 1 clove of garlic

[0188] Salt and pepper to taste

[0189] Cooking instructions:

[0190] 1. Cut the chicken breast into bite-sized pieces.

[0191] 2. Mince the garlic.

[0192] 3. Melt the butter in a frying pan and sauté the garlic.

[0193] 4. Add the chicken and stir-fry until it is nicely browned.

[0194] 5. Add soy sauce and adjust the taste.

[0195] Points to note:

[0196] Be careful not to burn the garlic.

[0197] After adding the soy sauce, adjust the temperature so that it doesn't get too hot.

[0198] The generated recipe is converted back into JSON format and sent to the user's terminal as an HTTP response. The user's terminal parses the received data and displays the recipe in a visually easy-to-understand format.

[0199] Furthermore, the system includes a function to automatically order the necessary ingredients from online delivery services based on the generated recipe. This allows users to order the necessary ingredients through a delivery service immediately after reviewing the recipe. Through this process, users can easily be presented with new recipes and simultaneously procure the necessary ingredients to prepare them.

[0200] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0201] Step 1:

[0202] The user enters their desired conditions using a smartphone application. This information includes the ingredients to be used, cooking time, type of dish, and difficulty level. For example, they might enter "a simple chicken dish that can be made in under 20 minutes." These conditions are converted into JSON data by the device.

[0203] Step 2:

[0204] The terminal sends the entered JSON data to the server as an HTTP request. The server receives this request and parses its contents. Specifically, the server's HTTP request processing functions, provided by Node.js and Express, are used.

[0205] Step 3:

[0206] The server analyzes the conditions and inputs them as a prompt to the generative AI. The prompt takes the following form: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes." After the prompt is generated, it is sent to the OpenAI GPT-4 model.

[0207] Step 4:

[0208] A generative AI (GPT-4 model) generates a new cooking recipe based on the prompt. This generation process includes ingredients that meet the specified criteria, cooking steps, and notes. The generated recipe is returned to the server. At this point, the output is specific recipe information.

[0209] Step 5:

[0210] The server converts the received recipe information into JSON format and sends it to the user's terminal as an HTTP response. Here, the input is the recipe information received from the generative AI, and the output is the response data returned to the user's terminal.

[0211] Step 6:

[0212] The device parses the received JSON data and displays it to the user in a visually easy-to-understand format. Specifically, the recipe's ingredient list, cooking instructions, and notes are displayed on a React Native interface. The user device's specific actions are to parse and display the received data.

[0213] Step 7:

[0214] The system automatically sends data on the necessary ingredients to a delivery service based on the generated recipe. This process uses the ingredient list provided in the recipe to issue an order to the online delivery service's API. This eliminates the need for users to manually place orders, allowing the system to automatically procure the necessary ingredients.

[0215] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0216] ---

[0217] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[0218] First, the user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. After entering the conditions, the user collects emotional data through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators.

[0219] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the system. When the user enters the conditions and clicks the "Request Suggestions" button, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc.

[0220] The device sends the converted JSON data to the server as an HTTP request. The server receives this request and parses the data. During the parsing process, the server analyzes emotional data to understand the user's current emotional state. Based on this analyzed data, the server combines generative AI and an emotion engine to generate a new recipe.

[0221] The server inputs analyzed conditions and emotional data into the generative AI. Based on the received prompts, the generative AI generates a new recipe, providing one that is appropriate for the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[0222] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[0223] material:

[0224] 300g chicken breast

[0225] 1 lemon

[0226] 2 cloves of garlic

[0227] 2 tablespoons olive oil

[0228] Salt and pepper to taste

[0229] Cooking instructions:

[0230] 1. Cut the chicken breast into bite-sized pieces.

[0231] 2. Grate the lemon zest and squeeze out the juice.

[0232] 3. Mince the garlic.

[0233] 4. Heat olive oil in a frying pan and sauté the garlic.

[0234] 5. Add the chicken and sauté until it has a nice golden brown color.

[0235] 6. Add the lemon juice and zest, and season with salt and pepper.

[0236] Points to note:

[0237] Be careful not to burn the garlic.

[0238] To prevent the lemon flavor from dissipating, do not overheat it.

[0239] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[0240] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[0241] This system allows users to receive new recipe suggestions with just a few clicks, and implementing them is easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. This system makes it easy for even beginner cooks to expand their culinary repertoire and improves the overall cooking experience.

[0242] ---

[0243] The following describes the processing flow.

[0244] ---

[0245] Step 1:

[0246] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, they might enter information such as "chicken," "easy," and "grilled."

[0247] Step 2:

[0248] After the user enters the necessary information, emotional data is collected through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators. For example, relaxed facial expressions and cheerful voice tones are collected.

[0249] Step 3:

[0250] The user reviews their input and clicks the "Request Proposal" button. The device then converts the user's entered conditions and collected sentiment data into JSON format. This data includes the entered ingredients, cooking methods, difficulty level, and sentiment index.

[0251] Step 4:

[0252] The device sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill", "Emotion": "Relax"}.

[0253] Step 5:

[0254] The server receives HTTP requests from the terminal and analyzes the data. Based on the analyzed data, the server utilizes an emotion engine to understand the user's emotional state. The emotion engine analyzes the user's emotional data and, for example, determines that "the user is relaxed."

[0255] Step 6:

[0256] Based on the analysis results from the emotion engine, the server inputs conditions and emotion data to the generative AI. For example, the prompt "A simple grilled chicken dish in a relaxed state" is sent to the generative AI.

[0257] Step 7:

[0258] Generative AI generates new recipes based on the prompts it receives. This process includes algorithms to combine ingredients, cooking steps, and precautions that meet the given conditions. For example, it might generate a recipe for "Lemon Garlic Chicken Sauté."

[0259] The generative AI generates the following recipe:

[0260] material:

[0261] 300g chicken breast

[0262] 1 lemon

[0263] 2 cloves of garlic

[0264] 2 tablespoons olive oil

[0265] Salt and pepper to taste

[0266] Cooking instructions:

[0267] 1. Cut the chicken breast into bite-sized pieces.

[0268] 2. Grate the lemon zest and squeeze out the juice.

[0269] 3. Mince the garlic.

[0270] 4. Heat olive oil in a frying pan and sauté the garlic.

[0271] 5. Add the chicken and sauté until it has a nice golden brown color.

[0272] 6. Add the lemon juice and zest, and season with salt and pepper.

[0273] Points to note:

[0274] Be careful not to burn the garlic.

[0275] To prevent the lemon flavor from dissipating, do not overheat it.

[0276] Step 8:

[0277] The generated recipe is converted into JSON format by the server and sent to the terminal as an HTTP response. For example, data such as {"Ingredients": [{"Chicken breast": "300g"}, {"Lemon": "1 piece"}, {"Garlic": "2 cloves"}, {"Olive oil": "2 tablespoons"}, {"Salt": "appropriate amount"}, {"Pepper": "appropriate amount"}], "Cooking steps": ["Cut the chicken breast into bite-sized pieces.", "Grate the lemon peel and squeeze the juice.", ...], "Points to note": ["Be careful not to burn the garlic.", "Do not overheat to avoid losing the flavor of the lemon."]} is sent.

[0278] Step 9:

[0279] The terminal analyzes the recipe data received from the server and displays it on the user interface. As a result, the user can check the ingredient list, cooking steps, and points to note. Supplementary information and adjustments based on the emotion data are also displayed.

[0280] Step 10:

[0281] Based on the presented recipe, the user starts cooking. The user prepares the ingredients and cooks according to the cooking steps. While paying attention to the points to note, the user finishes cooking safely and deliciously. During this process, the emotion engine monitors the user's continuous emotional state and provides real-time suggestions and advice as needed.

[0282] ---

[0283] The above is the description of the specific processing steps of the invention combined with the emotion engine.

[0284] (Example 2)

[0285] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0286] In the conventional recipe proposal system, there is a problem that since recipes are generated without considering the user's emotional state, proposals suitable for the user's current mood and state cannot be made. Also, the degree of personalization is low, and the user experience cannot be improved.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data, means for converting the conditions and emotional data into JSON format, means for transmitting the converted data to the server by communication, means for analyzing the data received by the server, means for generating a recipe using a generated AI model based on the analysis data, and means for displaying the generated recipe on the user interface. Thereby, it becomes possible to propose highly personalized recipes considering the user's emotional state.

[0288] The "means for inputting conditions desired by the user" refers to an interface or input device for inputting conditions such as ingredients, cooking methods, difficulty level, cooking time, etc. desired by the user.

[0289] The "means for collecting the user's emotional data" refers to devices such as cameras and microphones for collecting emotional indicators such as the user's facial expressions and voice tones.

[0290] The "means for converting the conditions and emotional data into JSON format" refers to software algorithms or programs for converting the conditions input by the user and the collected emotional data into JSON format data.

[0291] The "means for transmitting the converted data to the server by communication" refers to communication modules or protocols for transmitting the converted JSON data to the server via a communication network such as the Internet.

[0292] "Means for analyzing data received by the server" refers to software algorithms and analysis programs that analyze conditional data and emotional data received by the server to understand the user's desired characteristics and emotional state.

[0293] "Means of generating recipes using a generative AI model based on analyzed data" refers to software algorithms or generation programs that send prompts to a generative AI model based on analyzed data to generate new recipes.

[0294] "Means for displaying generated recipes on a user interface" refers to display devices or applications that display generated recipes on a user interface so that users can view them.

[0295] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[0296] The user first launches a browser or dedicated application to access the interface. The user then enters their desired ingredients, cooking method, difficulty level, cooking time, and other criteria. This input is done using an input device such as a keyboard or touchscreen.

[0297] Next, the user collects emotional data through a dedicated camera and microphone. This data can be collected using a webcam, a smartphone's built-in camera, or a microphone. This captures emotional indicators such as the user's facial expressions and voice tone in real time.

[0298] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the interface. When the user enters the conditions and clicks the "Request Suggestions" button, the device converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, cooking time, and sentiment indicators.

[0299] The terminal sends the converted JSON data to the server as an HTTP request. This transmission uses an internet-based communication module and the HTTP protocol. The server receives this request and parses the data.

[0300] The server uses analysis algorithms and emotion recognition engines to analyze the received data. During the analysis process, the server analyzes emotion data to understand the user's current emotional state. Then, based on the analyzed data, it uses a generative AI model to generate new recipes.

[0301] The server inputs analyzed conditions and emotional data into the generative AI model. Based on the received prompts, the generative AI model generates a new recipe, providing a recipe that suits the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[0302] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. The generative AI model will generate a recipe like this:

[0303] material:

[0304] 300g chicken breast

[0305] 1 lemon

[0306] 2 cloves of garlic

[0307] 2 tablespoons of olive oil

[0308] Appropriate amounts of salt and pepper

[0309] Cooking steps:

[0310] 1. Cut the chicken breast into bite-sized pieces.

[0311] 2. Grate the lemon peel and squeeze the juice.

[0312] 3. Mince the garlic.

[0313] 4. Heat the olive oil in a frying pan and sauté the garlic.

[0314] 5. Add the chicken and sauté until it gets a nice grilled color.

[0315] 6. Add the lemon juice and peel and season with salt and pepper.

[0316] Points to note:

[0317] Be careful not to let the garlic burn.

[0318] Don't overheat to prevent the lemon flavor from escaping.

[0319] The generated recipe is converted into JSON format by the server and sent to the terminal as an HTTP response. The terminal analyzes the recipe data received from the server and displays it on the user interface. As a result, the user can check the ingredient list, cooking steps, and points to note. Also, supplementary information and adjustments based on sentiment data are displayed.

[0320] Based on the presented recipe, the user starts cooking. The user prepares the ingredients and cooks according to the cooking steps. While paying attention to the points to note, the user finishes cooking safely and deliciously. During this process, the sentiment engine monitors the user's continuous sentiment state and provides real-time suggestions and advice as needed.

[0321] An example of a prompt statement is as follows:

[0322] "Please suggest some simple chicken recipes. The user is relaxed."

[0323] In this way, the system allows users to receive new recipe suggestions with just a few clicks, and implementing them is extremely easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized recipe suggestions. This makes it easy for even novice cooks to expand their culinary repertoire and improves their overall cooking experience.

[0324] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0325] Step 1:

[0326] The user launches a browser or dedicated application and accesses the interface. The user enters their desired conditions, such as ingredients (e.g., chicken), cooking method (e.g., grilling), difficulty level (e.g., easy), and cooking time (e.g., within 30 minutes). The entered conditions are saved on the device.

[0327] input:

[0328] Ingredients, cooking method, difficulty level, cooking time

[0329] output:

[0330] Data including user conditions (e.g., Ingredients: Chicken, Cooking method: Grilling, Difficulty: Easy, Cooking time: 30 minutes or less)

[0331] Specific actions:

[0332] Enter the conditions into the interface.

[0333] Click the "Request a recipe" button.

[0334] Step 2:

[0335] Users collect emotional data through a dedicated camera and microphone. The camera captures the user's facial expressions, and the microphone records the tone of their voice. This data is sent to an emotion analysis engine.

[0336] input:

[0337] User facial expressions and voice data

[0338] output:

[0339] Emotional analysis data (e.g., Relaxation)

[0340] Specific actions:

[0341] She smiles at the camera.

[0342] He speaks into the microphone in a gentle voice.

[0343] Step 3:

[0344] The device converts the user-inputted conditions and collected sentiment data into JSON format. This conversion is performed using a dedicated software algorithm.

[0345] input:

[0346] Ingredients, cooking method, difficulty level, cooking time, sentiment analysis data

[0347] output:

[0348] Data in JSON format (Example: {"Ingredients": "Chicken", "Cooking Method": "Grill", "Difficulty": "Easy", "Cooking Time": "Under 30 minutes", "Emotion": "Relaxed"})

[0349] Specific actions:

[0350] The software retrieves the input conditions and sentiment data from the terminal and converts them into JSON format.

[0351] Step 4:

[0352] The terminal sends the converted JSON data to the server as an HTTP request. HTTP is used as the communication protocol.

[0353] input:

[0354] Data in JSON format

[0355] output:

[0356] HTTP request sent to the server

[0357] Specific actions:

[0358] The device sends data to the server via the internet.

[0359] Step 5:

[0360] The server receives an HTTP request and parses the transmitted data. This parsing uses a sentiment analysis engine and data analysis algorithms.

[0361] input:

[0362] JSON data of the received HTTP request

[0363] output:

[0364] Analyzed user conditions and sentiment data

[0365] Specific actions:

[0366] The server executes a program to analyze the data it receives.

[0367] Step 6:

[0368] The server generates recipes using a generative AI model based on the analyzed data. The generative AI model receives a prompt such as: "Please suggest a simple chicken recipe. The user's mood is relaxed." The generative AI model then generates a new recipe.

[0369] input:

[0370] Analyzed condition and sentiment data

[0371] output:

[0372] Generated recipe data

[0373] Specific actions:

[0374] A prompt message is sent to the generative AI model to retrieve a new recipe.

[0375] Step 7:

[0376] The server converts the generated recipe data into JSON format and sends it to the terminal as an HTTP response.

[0377] input:

[0378] Recipe data

[0379] output:

[0380] Recipe data in JSON format

[0381] Specific actions:

[0382] The server converts the generated recipe into JSON format and sends it as an HTTP response.

[0383] Step 8:

[0384] The terminal parses the JSON-formatted recipe data received from the server and displays it on the user interface. Users can check the ingredient list, cooking instructions, and important notes.

[0385] input:

[0386] Recipe data in JSON format

[0387] output:

[0388] Visually displayed recipe information

[0389] Specific actions:

[0390] The device analyzes the recipe data and displays it on the screen.

[0391] Step 9:

[0392] The user begins cooking based on the provided recipe. During cooking, the emotion engine monitors the user's emotional state and provides real-time suggestions and advice as needed.

[0393] input:

[0394] Real-time sentiment data

[0395] output:

[0396] Real-time suggestions and advice

[0397] Specific actions:

[0398] Users provide emotional data through the camera and microphone, and the device provides corresponding feedback.

[0399] (Application Example 2)

[0400] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0401] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in recipes that are not suitable for the user's mood or stress level. Furthermore, it was difficult to instantly suggest recipes that matched the user's mood or purchasing intent for the day. This led to dissatisfaction with the suggested recipes, making it difficult for users to continue using the system.

[0402] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data through a dedicated camera and microphone, means including an emotion engine for analyzing the collected emotional data, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions and emotional data received by the server, and means for providing the generated recipe to the user. This makes it possible to suggest personalized recipes based on the user's emotional state, thereby improving user satisfaction and continued use of the system.

[0403] "A means for users to input their desired conditions" refers to a means of providing an interface for users to input conditions such as the ingredients, cooking method, difficulty level, and cooking time for the dishes they want.

[0404] "Means for sending entered conditions to a server" refers to means that have the function of converting conditions entered by the user into digital data and sending that data to a server via a network.

[0405] "Methods for collecting user emotional data through dedicated cameras and microphones" refers to methods of collecting emotional indicators such as the user's facial expressions and voice tone using cameras and microphones, and storing them as digital data.

[0406] "Means including an emotion engine for analyzing collected emotion data" refers to means including algorithms and software for analyzing emotion data collected by a dedicated camera or microphone and determining the user's emotional state.

[0407] "A method for generating recipes using generative AI to generate new cooking recipes" refers to a method of creating new cooking recipes using a generative AI model based on input conditions and sentiment data.

[0408] "Means of providing generated recipes to users" refers to means of displaying recipes generated by generative AI on the user interface.

[0409] "Means for the server to analyze conditional and emotional data for input into a generative AI" refers to methods for analyzing received conditional and emotional data and converting it into a format that the generative AI can understand.

[0410] "List of ingredients, cooking instructions, and notes" refers to information that includes a list of ingredients needed to make the dish, specific cooking steps, and points to keep in mind during cooking.

[0411] This invention is a system that suggests new dishes based on conditions desired by the user, and by combining it with an emotion engine, it achieves more accurate recipe suggestions.

[0412] First, the user launches a dedicated application using a communication terminal. Accessing the application's interface, the user inputs conditions such as desired ingredients, cooking method, difficulty level, and cooking time.

[0413] Next, the user collects emotional data through a dedicated camera and microphone. This collects emotional indicators such as the user's facial expressions and voice tone. This data is analyzed by an emotion engine to determine the user's current emotional state.

[0414] After the conditions are entered, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc. The converted data is sent to the server as an HTTP request.

[0415] The server analyzes the received data and generates prompts for input to the generative AI based on the conditions and sentiment data. Examples of prompts include: "Please suggest recipes using chicken," "Please suggest simple dishes with short cooking times," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[0416] Generative AI generates new cooking recipes based on received prompt text. This process includes algorithms and sentiment data-based complementation to combine ingredients, cooking procedures, and precautions that meet the given conditions.

[0417] The generated recipe includes an ingredient list, cooking instructions, and notes, and is converted to JSON format by the server. The server sends this data to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface.

[0418] Users can view the generated recipe through their device and cook according to the provided ingredient list, cooking instructions, and precautions. Furthermore, an emotion engine monitors the user's emotional state in real time during cooking and can offer suggestions and advice as needed.

[0419] This system allows users to receive new recipe suggestions in just a few clicks, and making them easy to implement. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. Even beginners can easily expand their culinary horizons, making this a system that enhances the overall cooking experience.

[0420] The hardware used includes smartphone and PC cameras. The software used includes OpenCV (image processing library), EmotionAnalyzer (emotion analysis library), requests (HTTP request library), and JSON (data exchange format).

[0421] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0422] Step 1:

[0423] The user launches a dedicated application using a communication terminal and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. The entered conditions are temporarily stored on the terminal. Specific inputs include "chicken," "easy," and "under 30 minutes."

[0424] Step 2:

[0425] The user collects emotional data through a dedicated camera and microphone. This emotional data captures the user's facial expressions and voice tone in real time and transmits it to the device. Specifically, the camera photographs the user's face, and the voice input device records the user's voice.

[0426] Step 3:

[0427] The device analyzes the collected emotional data using EmotionAnalyzer. The analysis results in the user's current emotional state (e.g., "relaxed"). This emotional state data is also stored on the device.

[0428] Step 4:

[0429] The terminal converts the entered conditions and emotion data into JSON format. This data includes ingredients, cooking method, difficulty level, and emotion state. The generated JSON data is sent to the server as an HTTP request.

[0430] Step 5:

[0431] The server receives an HTTP request and parses the JSON data. It extracts conditional and sentiment data and generates prompts to input into the generative AI based on them. Examples of specific prompts include: "Please suggest a recipe using chicken," "Please suggest a simple dish with a short cooking time," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[0432] Step 6:

[0433] The server inputs prompts into the generative AI, which then generates a new recipe. This process involves algorithms that combine ingredients, cooking steps, and precautions that meet the specified criteria, along with calculations to supplement emotional data. The generated recipe includes an ingredient list, cooking steps, and precautions.

[0434] Step 7:

[0435] The server converts the generated recipe into JSON format and sends it to the terminal as an HTTP response. The terminal receives the response from the server and parses the data.

[0436] Step 8:

[0437] The device displays the analyzed recipe data in a user interface. Users can view the provided ingredient list, cooking instructions, and precautions. The user interface may also display real-time advice and suggestions to help during cooking.

[0438] Step 9:

[0439] The user begins cooking based on the provided recipe. During cooking, an emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed. This allows the user to proceed with cooking with peace of mind.

[0440] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0441] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0442] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0443] [Second Embodiment]

[0444] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0445] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0446] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0447] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0448] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0449] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0450] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0451] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0452] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0453] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0454] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0455] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0456] ---

[0457] This invention is a system that allows users to easily receive suggestions for new cooking recipes, and its implementation follows the steps below.

[0458] First, users access the system using a browser or a dedicated application. Users can enter their desired conditions on the interface. These conditions include the ingredients to be used, cooking time, type of dish, and difficulty level. For example, if a user wants a "simple chicken dish," they would enter the corresponding information. Once the user enters the conditions and clicks the "Request Suggestions" button, the terminal sends the entered conditions to the server.

[0459] The terminal converts the user's input into JSON data and sends it to the server as an HTTP request. The server receives this request and parses the data. Based on this parsed data, the server inputs conditions into a generative AI. The generative AI generates a new recipe based on the received conditions. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[0460] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[0461] material:

[0462] 300g chicken breast

[0463] 1 lemon

[0464] 2 cloves of garlic

[0465] 2 tablespoons olive oil

[0466] Salt and pepper to taste

[0467] Cooking instructions:

[0468] 1. Cut the chicken breast into bite-sized pieces.

[0469] 2. Grate the lemon zest and squeeze out the juice.

[0470] 3. Mince the garlic.

[0471] 4. Heat olive oil in a frying pan and sauté the garlic.

[0472] 5. Add the chicken and sauté until it has a nice golden brown color.

[0473] 6. Add the lemon juice and zest, and season with salt and pepper.

[0474] Points to note:

[0475] Be careful not to burn the garlic.

[0476] To prevent the lemon flavor from dissipating, do not overheat it.

[0477] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays the recipe to the user in an easy-to-read format. This allows the user to start cooking based on the suggested recipe.

[0478] This system allows users to receive new recipe suggestions with just a few clicks, and making them is easy. Users can create new dishes simply by following the provided ingredients and cooking instructions. In this way, the present invention provides a system that allows even cooking beginners to easily expand their culinary repertoire.

[0479] ---

[0480] The following describes the processing flow.

[0481] ---

[0482] Step 1:

[0483] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, if the user wants a "simple chicken dish," they would enter information such as "chicken," "simple," and "grilled."

[0484] Step 2:

[0485] The user enters the conditions and clicks the "Request Proposal" button. The device then converts the user's entered conditions into JSON data. This data includes the entered ingredients, cooking method, difficulty level, etc.

[0486] Step 3:

[0487] The terminal sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill"}.

[0488] Step 4:

[0489] The server receives HTTP requests from terminals and parses the data. Based on the parsed data, the server creates prompts to generate new cooking recipes. These prompts are then input into a generative AI.

[0490] Step 5:

[0491] The server inputs prompts to the generative AI. Based on the received prompts, the generative AI generates a new recipe. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the specified criteria.

[0492] Step 6:

[0493] Generative AI generates recipes based on given conditions. For example, it might generate a dish called "Lemon Garlic Chicken Sauté." This recipe includes the following information:

[0494] material:

[0495] 300g chicken breast

[0496] 1 lemon

[0497] 2 cloves of garlic

[0498] 2 tablespoons olive oil

[0499] Salt and pepper to taste

[0500] Cooking instructions:

[0501] 1. Cut the chicken breast into bite-sized pieces.

[0502] 2. Grate the lemon zest and squeeze out the juice.

[0503] 3. Mince the garlic.

[0504] 4. Heat olive oil in a frying pan and sauté the garlic.

[0505] 5. Add the chicken and sauté until it has a nice golden brown color.

[0506] 6. Add the lemon juice and zest, and season with salt and pepper.

[0507] Points to note:

[0508] Be careful not to burn the garlic.

[0509] To prevent the lemon flavor from dissipating, do not overheat it.

[0510] Step 7:

[0511] The server converts the generated recipe into JSON data and sends it to the terminal as an HTTP response.

[0512] Step 8:

[0513] The terminal analyzes the recipe data received from the server and displays it on the user interface. This allows the user to check the ingredient list, cooking instructions, and important notes.

[0514] Step 9:

[0515] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking instructions. They complete the dish safely and deliciously, paying attention to all precautions.

[0516] ---

[0517] The above is a detailed explanation of the processing steps of this system.

[0518] (Example 1)

[0519] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0520] Conventional recipe suggestion systems have struggled to generate new recipes that are appropriate and timely in response to user input. Furthermore, the generated recipes sometimes lacked comprehensive ingredient lists, cooking instructions, and important notes, making them difficult for users to use.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0522] In this invention, the server includes means for inputting conditions desired by the user, means for transmitting the input conditions to the server, means for the server to parse the received conditions in JSON format and input the parsed data into a generation AI model, means for generating a new cooking recipe based on the conditions using the generation AI model, and means for transmitting the generated recipe to a terminal and displaying the recipe on the terminal. This makes it possible to quickly generate a new cooking recipe based on the conditions desired by the user and provide a recipe that includes a detailed list of ingredients, cooking procedures, and precautions.

[0523] "Means for users to input desired conditions" refers to methods and devices for users to input cooking-related conditions on an interface.

[0524] "Means for sending entered conditions to the server" means a method and device for sending entered conditions from a terminal to a server using a communication protocol (e.g., HTTP).

[0525] "Means for a server to parse the conditions it receives in JSON format and input the parsed data into a generating AI model" means a method and apparatus for a server to parse the conditions it receives in JSON format using a data analysis library and input the analysis results into a generating AI model.

[0526] "Means for generating new recipes based on conditions using a generative AI model" means a method and apparatus for generating new recipes that match user conditions using a generative AI model.

[0527] "Means for sending a generated recipe to a terminal and displaying the recipe on the terminal" means a method and apparatus for converting a generated recipe into JSON format, sending it from the server to the terminal, and displaying it on the terminal in a format that is easy for the user to view.

[0528] "Means for converting and analyzing conditions in JSON format for input into a generated AI model by the server" means a method and apparatus for converting raw data received by the server into JSON format and analyzing those conditions.

[0529] "The generated recipe includes a list of ingredients, cooking instructions, and notes" means that the recipe output by the generating AI model includes a specific list of ingredients, detailed cooking instructions, and notes to keep in mind while cooking.

[0530] Modes for carrying out the invention

[0531] This invention provides a system that allows users to easily receive suggestions for new cooking recipes, and its implementation involves the following steps.

[0532] First, users access this system using an internet-connected device (such as a PC, smartphone, or tablet). To access the system, users need a web browser (e.g., Chrome, Firefox) or a dedicated application. On this interface, users enter their desired ingredients, cooking time, type of dish, difficulty level, and other preferences. For example, if they want a simple chicken dish, they would enter the corresponding information.

[0533] When a user clicks the "Request Proposal" button, the device converts the entered conditions into JSON data and sends it to the server as an HTTP request. The communication protocol used at this time is HTTP.

[0534] The server receives this request and parses the conditions in JSON format using a data analysis library (e.g., FastAPI, Flask). The parsed data is then input into a generative AI model (e.g., GPT-3, BERT). The generative AI model generates a new recipe based on the received conditions. This generation process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[0535] The generated recipe is converted back to JSON format on the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays it to the user in an easy-to-understand format. Frontend libraries and frameworks such as JavaScript and React may be used at this stage.

[0536] For example, if a new dish called "Lemon Garlic Chicken Sauté" is proposed, the generated recipe would look like this:

[0537] material:

[0538] 300g chicken breast

[0539] 1 lemon

[0540] 2 cloves of garlic

[0541] 2 tablespoons olive oil

[0542] Salt and pepper to taste

[0543] Cooking instructions:

[0544] 1. Cut the chicken breast into bite-sized pieces.

[0545] 2. Grate the lemon zest and squeeze out the juice.

[0546] 3. Mince the garlic.

[0547] 4. Heat olive oil in a frying pan and sauté the garlic.

[0548] 5. Add the chicken and sauté until it has a nice golden brown color.

[0549] 6. Add the lemon juice and zest, and season with salt and pepper.

[0550] Points to note:

[0551] Be careful not to burn the garlic.

[0552] To prevent the lemon flavor from dissipating, do not overheat it.

[0553] The advantage of this system is that users can receive new recipe suggestions with just a few clicks, and the process is simple. Users can create new dishes simply by following the suggested ingredients and cooking instructions. In this way, the present invention makes it possible for even cooking beginners to easily expand their culinary repertoire.

[0554] Examples of prompt statements are as follows:

[0555] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[0556] By inputting this prompt into the AI ​​generation model, a recipe suitable for the given conditions is generated and provided to the user.

[0557] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0558] System program processing flow

[0559] Step 1:

[0560] The user enters their desired conditions. The user inputs the ingredients they want to use, cooking time, type of dish, difficulty level, etc., on the interface. For example, they might select "chicken," "under 30 minutes," "sauté," and "easy." This generates input data based on the user's desired conditions. This input data is saved in JSON format.

[0561] Input: Conditions entered by the user in the interface

[0562] Output: Input data in JSON format

[0563] Step 2:

[0564] The terminal sends the input data to the server. When the user clicks the "Request Proposal" button, the terminal converts the entered conditions into JSON format data and sends it to the server as an HTTP request.

[0565] Input: Input data in JSON format

[0566] Output: HTTP request sent to the server

[0567] Step 3:

[0568] The server analyzes the received conditions. The server analyzes the received JSON data using a data analysis library (e.g., FastAPI, Flask) and inputs the analyzed data into the generating AI model. Specific data analysis steps include schema validation and extraction of necessary items.

[0569] Input: HTTP request in JSON format

[0570] Output: Analyzed data (Example: {"Ingredients": "Chicken", "Cooking time": "Under 30 minutes", "Type of dish": "Sauté", "Difficulty": "Easy"})

[0571] Step 4:

[0572] A generative AI model generates a new recipe. The server inputs the analyzed data as prompts into the generative AI model (e.g., GPT-3). The generative AI model generates a new recipe based on the given conditions. This process includes generating an ingredient list, cooking instructions, and notes.

[0573] Input: Analyzed data

[0574] Output: Generated recipe (Example: {"Ingredients": {...}, "Cooking Instructions": [...], "Notes": [...]})

[0575] Step 5:

[0576] The server converts the generated recipe into JSON format and sends it to the terminal. The generated recipe is then converted back into JSON format within the server and sent to the terminal as an HTTP response. Conversion and validation take place during this process.

[0577] Input: Generated recipe

[0578] Output: HTTP response in JSON format

[0579] Step 6:

[0580] The device parses and displays the recipe. The device reads the received data using a JSON parsing library and displays the recipe to the user in an easy-to-understand format. This display may utilize front-end libraries such as JavaScript or React.

[0581] Input: HTTP response in JSON format

[0582] Output: Recipe display in a format viewable by the user.

[0583] Example prompt statements

[0584] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[0585] By inputting this prompt into the AI ​​generation model, a recipe suitable for the given conditions is generated and provided to the user.

[0586] (Application Example 1)

[0587] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0588] Conventional recipe suggestion systems only provide users with suggested recipes, leaving them responsible for purchasing and arranging for the delivery of ingredients. Furthermore, there was a lack of systems capable of adequately handling recipe generation based on specific conditions. Additionally, there was insufficient means to efficiently procure the necessary ingredients when generating new recipes.

[0589] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0590] In this invention, the server includes means for inputting desired conditions from the user, means for transmitting the input conditions to the server, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions received by the server, means for ordering the necessary ingredients through a delivery service based on the generated recipe, and means for providing the generated recipe to the user. As a result, the user can not only be offered cooking recipes based on their desired conditions, but also have the delivery of the necessary ingredients for those recipes arranged all at once.

[0591] "A means for users to input their desired conditions" refers to a component that provides an interface where users can input conditions such as the ingredients they want to use, cooking time, type of dish, and difficulty level.

[0592] "Means for sending entered conditions to the server" refers to a data communication function for sending conditions entered by the user to the server via the network.

[0593] "A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server" refers to a function in which the server analyzes the user's conditions and generates new cooking recipes using a generative AI model based on those conditions.

[0594] "A means of ordering necessary ingredients through a delivery service based on a generated recipe" refers to a function that automatically orders the necessary ingredients through an online delivery service based on the ingredient list described in the generated recipe.

[0595] "Means of providing generated recipes to users" refers to a function for displaying or providing generated new cooking recipes to the user's device.

[0596] This invention is a system that proposes new recipes based on the user's desired conditions and allows the user to order the necessary ingredients through a delivery service based on those recipes. This system is configured as follows:

[0597] First, users access the system using a dedicated smartphone application. On the interface, users can input their desired conditions (for example, ingredients to use, cooking time, type of dish, difficulty level, etc.). This allows users to input specific instructions such as "a simple dish using chicken."

[0598] The entered conditions are converted into JSON data and sent to the server as an HTTP request. This communication is implemented using, for example, a frontend built with React Native and a backend using Node.js and Express.

[0599] The server receives the request and analyzes the data. The analyzed data is then input as a prompt to the generative AI based on OpenAI's GPT-4 model. An example of a prompt is: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes."

[0600] Generative AI generates new recipes based on the conditions it receives. This generation process includes algorithms to consider ingredients that meet the conditions, cooking procedures, and points to note. For example, if a new dish called "Chicken Stir-fry with Butter and Soy Sauce" is proposed, the generated recipe will include the following details:

[0601] material:

[0602] 200g chicken breast

[0603] 30g butter

[0604] 2 tablespoons soy sauce

[0605] 1 clove of garlic

[0606] Salt and pepper to taste

[0607] Cooking instructions:

[0608] 1. Cut the chicken breast into bite-sized pieces.

[0609] 2. Mince the garlic.

[0610] 3. Melt the butter in a frying pan and sauté the garlic.

[0611] 4. Add the chicken and stir-fry until it is nicely browned.

[0612] 5. Add soy sauce and adjust the taste.

[0613] Points to note:

[0614] Be careful not to burn the garlic.

[0615] After adding the soy sauce, adjust the temperature so that it doesn't get too hot.

[0616] The generated recipe is converted back into JSON format and sent to the user's terminal as an HTTP response. The user's terminal parses the received data and displays the recipe in a visually easy-to-understand format.

[0617] Furthermore, the system includes a function to automatically order the necessary ingredients from online delivery services based on the generated recipe. This allows users to order the necessary ingredients through a delivery service immediately after reviewing the recipe. Through this process, users can easily be presented with new recipes and simultaneously procure the necessary ingredients to prepare them.

[0618] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0619] Step 1:

[0620] The user enters their desired conditions using a smartphone application. This information includes the ingredients to be used, cooking time, type of dish, and difficulty level. For example, they might enter "a simple chicken dish that can be made in under 20 minutes." These conditions are converted into JSON data by the device.

[0621] Step 2:

[0622] The terminal sends the entered JSON data to the server as an HTTP request. The server receives this request and parses its contents. Specifically, the server's HTTP request processing functions, provided by Node.js and Express, are used.

[0623] Step 3:

[0624] The server analyzes the conditions and inputs them as a prompt to the generative AI. The prompt takes the following form: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes." After the prompt is generated, it is sent to the OpenAI GPT-4 model.

[0625] Step 4:

[0626] A generative AI (GPT-4 model) generates a new cooking recipe based on the prompt. This generation process includes ingredients that meet the specified criteria, cooking steps, and notes. The generated recipe is returned to the server. At this point, the output is specific recipe information.

[0627] Step 5:

[0628] The server converts the received recipe information into JSON format and sends it to the user's terminal as an HTTP response. Here, the input is the recipe information received from the generative AI, and the output is the response data returned to the user's terminal.

[0629] Step 6:

[0630] The device parses the received JSON data and displays it to the user in a visually easy-to-understand format. Specifically, the recipe's ingredient list, cooking instructions, and notes are displayed on a React Native interface. The user device's specific actions are parsing and displaying the received data.

[0631] Step 7:

[0632] The system automatically transmits data on the necessary ingredients to a delivery service based on the generated recipe. This process uses the ingredient list provided in the recipe to issue an order to the online delivery service's API. This eliminates the need for users to manually place orders, allowing the system to automatically procure the necessary ingredients.

[0633] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0634] ---

[0635] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[0636] First, the user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. After entering the conditions, the user collects emotional data through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators.

[0637] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the system. When the user enters the conditions and clicks the "Request Suggestions" button, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc.

[0638] The device sends the converted JSON data to the server as an HTTP request. The server receives this request and parses the data. During the parsing process, the server analyzes emotional data to understand the user's current emotional state. Based on this analyzed data, the server combines generative AI and an emotion engine to generate a new recipe.

[0639] The server inputs analyzed conditions and emotional data into the generative AI. Based on the received prompts, the generative AI generates a new recipe, providing one that is appropriate for the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[0640] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[0641] material:

[0642] 300g chicken breast

[0643] 1 lemon

[0644] 2 cloves of garlic

[0645] 2 tablespoons olive oil

[0646] Salt and pepper to taste

[0647] Cooking instructions:

[0648] 1. Cut the chicken breast into bite-sized pieces.

[0649] 2. Grate the lemon zest and squeeze out the juice.

[0650] 3. Mince the garlic.

[0651] 4. Heat olive oil in a frying pan and sauté the garlic.

[0652] 5. Add the chicken and sauté until it has a nice golden brown color.

[0653] 6. Add the lemon juice and zest, and season with salt and pepper.

[0654] Points to note:

[0655] Be careful not to burn the garlic.

[0656] To prevent the lemon flavor from dissipating, do not overheat it.

[0657] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[0658] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[0659] This system allows users to receive new recipe suggestions with just a few clicks, and implementing them is easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. This system makes it easy for even beginner cooks to expand their culinary repertoire and improves the overall cooking experience.

[0660] ---

[0661] The following describes the processing flow.

[0662] ---

[0663] Step 1:

[0664] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, they might enter information such as "chicken," "easy," and "grilled."

[0665] Step 2:

[0666] After the user enters the necessary information, emotional data is collected through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators. For example, relaxed facial expressions and cheerful voice tones are collected.

[0667] Step 3:

[0668] The user reviews their input and clicks the "Request Proposal" button. The device then converts the user's entered conditions and collected sentiment data into JSON format. This data includes the entered ingredients, cooking methods, difficulty level, and sentiment index.

[0669] Step 4:

[0670] The device sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill", "Emotion": "Relax"}.

[0671] Step 5:

[0672] The server receives HTTP requests from the terminal and analyzes the data. Based on the analyzed data, the server utilizes an emotion engine to understand the user's emotional state. The emotion engine analyzes the user's emotional data and, for example, determines that "the user is relaxed."

[0673] Step 6:

[0674] Based on the analysis results from the emotion engine, the server inputs conditions and emotion data to the generative AI. For example, the prompt "A simple grilled chicken dish in a relaxed state" is sent to the generative AI.

[0675] Step 7:

[0676] Generative AI generates new cooking recipes based on the prompts it receives. This process includes algorithms to combine ingredients, cooking steps, and precautions that meet the given conditions. For example, it might generate a recipe for "Lemon Garlic Chicken Sauté."

[0677] The generative AI generates the following recipe:

[0678] material:

[0679] 300g chicken breast

[0680] 1 lemon

[0681] 2 cloves of garlic

[0682] 2 tablespoons olive oil

[0683] Salt and pepper to taste

[0684] Cooking instructions:

[0685] 1. Cut the chicken breast into bite-sized pieces.

[0686] 2. Grate the lemon zest and squeeze out the juice.

[0687] 3. Mince the garlic.

[0688] 4. Heat olive oil in a frying pan and sauté the garlic.

[0689] 5. Add the chicken and sauté until it has a nice golden brown color.

[0690] 6. Add the lemon juice and zest, and season with salt and pepper.

[0691] Points to note:

[0692] Be careful not to burn the garlic.

[0693] To prevent the lemon flavor from dissipating, do not overheat it.

[0694] Step 8:

[0695] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. For example, data such as {"Ingredients": [{"Chicken breast": "300g"}, {"Lemon": "1"}, {"Garlic": "2 cloves"}, {"Olive oil": "2 tablespoons"}, {"Salt": "to taste"}, {"Pepper": "to taste"}], "Cooking Instructions": ["Cut the chicken breast into bite-sized pieces.", "Grate the lemon zest and squeeze the juice.", ...], "Notes": ["Be careful not to burn the garlic.", "Do not overheat so that the lemon flavor does not dissipate."]} is sent.

[0696] Step 9:

[0697] The terminal analyzes recipe data received from the server and displays it on the user interface. This allows the user to check the ingredient list, cooking instructions, and important notes. Supplementary information and adjustments based on sentiment data are also displayed.

[0698] Step 10:

[0699] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[0700] ---

[0701] The above is a description of the specific processing steps of the invention that combines an emotion engine.

[0702] (Example 2)

[0703] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0704] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in a problem where they cannot provide suggestions suitable for the user's current mood or condition. Furthermore, they offer a low degree of personalization, failing to improve the user experience.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data, means for converting the conditions and emotional data into JSON format, means for transmitting the converted data to the server via communication, means for analyzing the data received by the server, means for generating a recipe using a generation AI model based on the analyzed data, and means for displaying the generated recipe on the user interface. This makes it possible to suggest highly personalized recipes that take into account the user's emotional state.

[0706] "Means for users to input their desired conditions" refers to interfaces or input devices for users to input conditions such as desired ingredients, cooking methods, difficulty level, and cooking time.

[0707] "Means of collecting user emotional data" refers to devices such as cameras and microphones used to collect emotional indicators such as the user's facial expressions and voice tone.

[0708] "Means for converting condition and sentiment data into JSON format" refers to software algorithms or programs for converting user-entered conditions and collected sentiment data into JSON format data.

[0709] "Means of sending converted data to a server via communication" refers to communication modules or protocols used to send converted JSON data to a server via a communication network such as the internet.

[0710] "Means for analyzing data received by the server" refers to software algorithms and analysis programs that analyze conditional data and emotional data received by the server to understand the user's desired characteristics and emotional state.

[0711] "Means of generating recipes using a generative AI model based on analyzed data" refers to software algorithms or generation programs that send prompts to a generative AI model based on analyzed data to generate new recipes.

[0712] "Means for displaying generated recipes on a user interface" refers to display devices or applications that display generated recipes on a user interface so that users can view them.

[0713] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[0714] The user first launches a browser or dedicated application to access the interface. The user then enters their desired ingredients, cooking method, difficulty level, cooking time, and other criteria. This input is done using an input device such as a keyboard or touchscreen.

[0715] Next, the user collects emotional data through a dedicated camera and microphone. This data can be collected using a webcam, a smartphone's built-in camera, or a microphone. This captures emotional indicators such as the user's facial expressions and voice tone in real time.

[0716] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the interface. When the user enters the conditions and clicks the "Request Suggestions" button, the device converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, cooking time, and sentiment indicators.

[0717] The terminal sends the converted JSON data to the server as an HTTP request. This transmission uses an internet-based communication module and the HTTP protocol. The server receives this request and parses the data.

[0718] The server uses analysis algorithms and emotion recognition engines to analyze the received data. During the analysis process, the server analyzes emotion data to understand the user's current emotional state. Then, based on the analyzed data, it uses a generative AI model to generate new recipes.

[0719] The server inputs analyzed conditions and emotional data into the generative AI model. Based on the received prompts, the generative AI model generates a new recipe, providing a recipe that suits the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[0720] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. The generative AI model will generate a recipe like this:

[0721] material:

[0722] 300g chicken breast

[0723] 1 lemon

[0724] 2 cloves of garlic

[0725] 2 tablespoons olive oil

[0726] Salt and pepper to taste

[0727] Cooking instructions:

[0728] 1. Cut the chicken breast into bite-sized pieces.

[0729] 2. Grate the lemon zest and squeeze out the juice.

[0730] 3. Mince the garlic.

[0731] 4. Heat olive oil in a frying pan and sauté the garlic.

[0732] 5. Add the chicken and sauté until it has a nice golden brown color.

[0733] 6. Add the lemon juice and zest, and season with salt and pepper.

[0734] Points to note:

[0735] Be careful not to burn the garlic.

[0736] To prevent the lemon flavor from dissipating, do not overheat it.

[0737] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[0738] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[0739] An example of a prompt statement is as follows:

[0740] "Please suggest some simple chicken recipes. The user is relaxed."

[0741] In this way, the system allows users to receive new recipe suggestions with just a few clicks, and implementing them is extremely easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized recipe suggestions. This makes it easy for even novice cooks to expand their culinary repertoire and improves their overall cooking experience.

[0742] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0743] Step 1:

[0744] The user launches a browser or dedicated application and accesses the interface. The user enters their desired conditions, such as ingredients (e.g., chicken), cooking method (e.g., grilling), difficulty level (e.g., easy), and cooking time (e.g., within 30 minutes). The entered conditions are saved on the device.

[0745] input:

[0746] Ingredients, cooking method, difficulty level, cooking time

[0747] output:

[0748] Data including user conditions (e.g., Ingredients: Chicken, Cooking method: Grilling, Difficulty: Easy, Cooking time: 30 minutes or less)

[0749] Specific actions:

[0750] Enter the conditions into the interface.

[0751] Click the "Request a recipe" button.

[0752] Step 2:

[0753] Users collect emotional data through a dedicated camera and microphone. The camera captures the user's facial expressions, and the microphone records the tone of their voice. This data is sent to an emotion analysis engine.

[0754] input:

[0755] User facial expressions and voice data

[0756] output:

[0757] Emotional analysis data (e.g., Relaxation)

[0758] Specific actions:

[0759] She smiles at the camera.

[0760] He speaks into the microphone in a gentle voice.

[0761] Step 3:

[0762] The device converts the user-inputted conditions and collected sentiment data into JSON format. This conversion is performed using a dedicated software algorithm.

[0763] input:

[0764] Ingredients, cooking method, difficulty level, cooking time, sentiment analysis data

[0765] output:

[0766] Data in JSON format (Example: {"Ingredients": "Chicken", "Cooking Method": "Grill", "Difficulty": "Easy", "Cooking Time": "Under 30 minutes", "Emotion": "Relaxed"})

[0767] Specific actions:

[0768] The software retrieves the input conditions and sentiment data from the terminal and converts them into JSON format.

[0769] Step 4:

[0770] The terminal sends the converted JSON data to the server as an HTTP request. HTTP is used as the communication protocol.

[0771] input:

[0772] Data in JSON format

[0773] output:

[0774] HTTP request sent to the server

[0775] Specific actions:

[0776] The device sends data to the server via the internet.

[0777] Step 5:

[0778] The server receives an HTTP request and parses the transmitted data. This parsing uses a sentiment analysis engine and data analysis algorithms.

[0779] input:

[0780] JSON data of the received HTTP request

[0781] output:

[0782] Analyzed user conditions and sentiment data

[0783] Specific actions:

[0784] The server executes a program to analyze the data it receives.

[0785] Step 6:

[0786] The server generates recipes using a generative AI model based on the analyzed data. The generative AI model receives a prompt such as: "Please suggest a simple chicken recipe. The user's mood is relaxed." The generative AI model then generates a new recipe.

[0787] input:

[0788] Analyzed condition and sentiment data

[0789] output:

[0790] Generated recipe data

[0791] Specific actions:

[0792] A prompt message is sent to the generative AI model to retrieve a new recipe.

[0793] Step 7:

[0794] The server converts the generated recipe data into JSON format and sends it to the terminal as an HTTP response.

[0795] input:

[0796] Recipe data

[0797] output:

[0798] Recipe data in JSON format

[0799] Specific actions:

[0800] The server converts the generated recipe into JSON format and sends it as an HTTP response.

[0801] Step 8:

[0802] The terminal parses the JSON-formatted recipe data received from the server and displays it on the user interface. Users can check the ingredient list, cooking instructions, and important notes.

[0803] input:

[0804] Recipe data in JSON format

[0805] output:

[0806] Visually displayed recipe information

[0807] Specific actions:

[0808] The device analyzes the recipe data and displays it on the screen.

[0809] Step 9:

[0810] The user begins cooking based on the provided recipe. During cooking, the emotion engine monitors the user's emotional state and provides real-time suggestions and advice as needed.

[0811] input:

[0812] Real-time sentiment data

[0813] output:

[0814] Real-time suggestions and advice

[0815] Specific actions:

[0816] Users provide emotional data through the camera and microphone, and the device provides corresponding feedback.

[0817] (Application Example 2)

[0818] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0819] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in recipes that are not suitable for the user's mood or stress level. Furthermore, it was difficult to instantly suggest recipes that matched the user's mood or purchasing intent for the day. This led to dissatisfaction with the suggested recipes, making it difficult for users to continue using the system.

[0820] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data through a dedicated camera and microphone, means including an emotion engine for analyzing the collected emotional data, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions and emotional data received by the server, and means for providing the generated recipe to the user. This makes it possible to suggest personalized recipes based on the user's emotional state, thereby improving user satisfaction and continued use of the system.

[0821] "Means for users to input desired conditions" refers to providing an interface for users to input conditions such as the ingredients, cooking method, difficulty level, and cooking time for the dishes they want.

[0822] "Means for sending entered conditions to the server" refers to means that have the function of converting conditions entered by the user into digital data and sending that data to the server via the network.

[0823] "Methods for collecting user emotional data through dedicated cameras and microphones" refers to methods of collecting emotional indicators such as the user's facial expressions and voice tone using cameras and microphones, and storing them as digital data.

[0824] "Means including an emotion engine for analyzing collected emotion data" refers to means including algorithms and software for analyzing emotion data collected by a dedicated camera or microphone and determining the user's emotional state.

[0825] "A method for generating recipes using generative AI to generate new cooking recipes" refers to a method of creating new cooking recipes using a generative AI model based on input conditions and sentiment data.

[0826] "Means of providing generated recipes to users" refers to means of displaying recipes generated by generative AI on the user interface.

[0827] "Means for the server to analyze conditional and emotional data for input into a generative AI" refers to methods for analyzing received conditional and emotional data and converting it into a format that the generative AI can understand.

[0828] "List of ingredients, cooking instructions, and notes" refers to information that includes a list of ingredients needed to make the dish, specific cooking steps, and points to keep in mind during cooking.

[0829] This invention is a system that suggests new dishes based on conditions desired by the user, and by combining it with an emotion engine, it achieves more accurate recipe suggestions.

[0830] First, the user launches a dedicated application using a communication terminal. Accessing the application's interface, the user inputs conditions such as desired ingredients, cooking method, difficulty level, and cooking time.

[0831] Next, the user collects emotional data through a dedicated camera and microphone. This collects emotional indicators such as the user's facial expressions and voice tone. This data is analyzed by an emotion engine to determine the user's current emotional state.

[0832] After the conditions are entered, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc. The converted data is sent to the server as an HTTP request.

[0833] The server analyzes the received data and generates prompts for input to the generative AI based on the conditions and sentiment data. Examples of prompts include: "Please suggest recipes using chicken," "Please suggest simple dishes with short cooking times," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[0834] Generative AI generates new cooking recipes based on received prompt text. This process includes algorithms and sentiment data-based complementation to combine ingredients, cooking procedures, and precautions that meet the given conditions.

[0835] The generated recipe includes an ingredient list, cooking instructions, and notes, and is converted to JSON format by the server. The server sends this data to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface.

[0836] Users can view the generated recipe through their device and cook according to the provided ingredient list, cooking instructions, and precautions. Furthermore, an emotion engine monitors the user's emotional state in real time during cooking and can offer suggestions and advice as needed.

[0837] This system allows users to receive new recipe suggestions in just a few clicks, and making them easy to implement. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. Even beginners can easily expand their culinary horizons, making this a system that enhances the overall cooking experience.

[0838] The hardware used includes smartphone and PC cameras. The software used includes OpenCV (image processing library), EmotionAnalyzer (emotion analysis library), requests (HTTP request library), and JSON (data exchange format).

[0839] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0840] Step 1:

[0841] The user launches a dedicated application using a communication terminal and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. The entered conditions are temporarily stored on the terminal. Specific inputs include "chicken," "easy," and "under 30 minutes."

[0842] Step 2:

[0843] The user collects emotional data through a dedicated camera and microphone. This emotional data captures the user's facial expressions and voice tone in real time and transmits it to the device. Specifically, the camera photographs the user's face, and the voice input device records the user's voice.

[0844] Step 3:

[0845] The device analyzes the collected emotional data using EmotionAnalyzer. The analysis results in the user's current emotional state (e.g., "relaxed"). This emotional state data is also stored on the device.

[0846] Step 4:

[0847] The terminal converts the entered conditions and emotion data into JSON format. This data includes ingredients, cooking method, difficulty level, and emotion state. The generated JSON data is sent to the server as an HTTP request.

[0848] Step 5:

[0849] The server receives an HTTP request and parses the JSON data. It extracts conditional and sentiment data and generates prompts to input into the generative AI based on them. Examples of specific prompts include: "Please suggest a recipe using chicken," "Please suggest a simple dish with a short cooking time," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[0850] Step 6:

[0851] The server inputs prompts into the generative AI, which then generates a new recipe. This process involves algorithms that combine ingredients, cooking steps, and precautions that meet the specified criteria, along with calculations to supplement emotional data. The generated recipe includes an ingredient list, cooking steps, and precautions.

[0852] Step 7:

[0853] The server converts the generated recipe into JSON format and sends it to the terminal as an HTTP response. The terminal receives the response from the server and parses the data.

[0854] Step 8:

[0855] The device displays the analyzed recipe data in a user interface. Users can view the provided ingredient list, cooking instructions, and precautions. The user interface may also display real-time advice and suggestions to help during cooking.

[0856] Step 9:

[0857] The user begins cooking based on the provided recipe. During cooking, an emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed. This allows the user to proceed with cooking with peace of mind.

[0858] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0859] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0860] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0861] [Third Embodiment]

[0862] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0863] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0864] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0865] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0866] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0867] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0868] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0869] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0870] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0871] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0872] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0873] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0874] ---

[0875] This invention is a system that allows users to easily receive suggestions for new cooking recipes, and its implementation follows the steps below.

[0876] First, users access the system using a browser or a dedicated application. Users can enter their desired conditions on the interface. These conditions include the ingredients to be used, cooking time, type of dish, and difficulty level. For example, if a user wants a "simple chicken dish," they would enter the corresponding information. Once the user enters the conditions and clicks the "Request Suggestions" button, the terminal sends the entered conditions to the server.

[0877] The terminal converts the user's input into JSON data and sends it to the server as an HTTP request. The server receives this request and parses the data. Based on this parsed data, the server inputs conditions into a generative AI. The generative AI generates a new recipe based on the received conditions. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[0878] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[0879] material:

[0880] 300g chicken breast

[0881] 1 lemon

[0882] 2 cloves of garlic

[0883] 2 tablespoons olive oil

[0884] Salt and pepper to taste

[0885] Cooking instructions:

[0886] 1. Cut the chicken breast into bite-sized pieces.

[0887] 2. Grate the lemon zest and squeeze out the juice.

[0888] 3. Mince the garlic.

[0889] 4. Heat olive oil in a frying pan and sauté the garlic.

[0890] 5. Add the chicken and sauté until it has a nice golden brown color.

[0891] 6. Add the lemon juice and zest, and season with salt and pepper.

[0892] Points to note:

[0893] Be careful not to burn the garlic.

[0894] To prevent the lemon flavor from dissipating, do not overheat it.

[0895] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays the recipe to the user in an easy-to-read format. This allows the user to start cooking based on the suggested recipe.

[0896] This system allows users to receive new recipe suggestions with just a few clicks, and making them is easy. Users can create new dishes simply by following the provided ingredients and cooking instructions. In this way, the present invention provides a system that allows even cooking beginners to easily expand their culinary repertoire.

[0897] ---

[0898] The following describes the processing flow.

[0899] ---

[0900] Step 1:

[0901] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, if the user wants a "simple chicken dish," they would enter information such as "chicken," "simple," and "grilled."

[0902] Step 2:

[0903] The user enters the conditions and clicks the "Request Proposal" button. The device then converts the user's entered conditions into JSON data. This data includes the entered ingredients, cooking method, difficulty level, etc.

[0904] Step 3:

[0905] The terminal sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill"}.

[0906] Step 4:

[0907] The server receives HTTP requests from terminals and parses the data. Based on the parsed data, the server creates prompts to generate new cooking recipes. These prompts are then input into a generative AI.

[0908] Step 5:

[0909] The server inputs prompts to the generative AI. Based on the received prompts, the generative AI generates a new recipe. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the specified criteria.

[0910] Step 6:

[0911] Generative AI generates recipes based on given conditions. For example, it might generate a dish called "Lemon Garlic Chicken Sauté." This recipe includes the following information:

[0912] material:

[0913] 300g chicken breast

[0914] 1 lemon

[0915] 2 cloves of garlic

[0916] 2 tablespoons olive oil

[0917] Salt and pepper to taste

[0918] Cooking instructions:

[0919] 1. Cut the chicken breast into bite-sized pieces.

[0920] 2. Grate the lemon zest and squeeze out the juice.

[0921] 3. Mince the garlic.

[0922] 4. Heat olive oil in a frying pan and sauté the garlic.

[0923] 5. Add the chicken and sauté until it has a nice golden brown color.

[0924] 6. Add the lemon juice and zest, and season with salt and pepper.

[0925] Points to note:

[0926] Be careful not to burn the garlic.

[0927] To prevent the lemon flavor from dissipating, do not overheat it.

[0928] Step 7:

[0929] The server converts the generated recipe into JSON data and sends it to the terminal as an HTTP response.

[0930] Step 8:

[0931] The terminal analyzes the recipe data received from the server and displays it on the user interface. This allows the user to check the ingredient list, cooking instructions, and important notes.

[0932] Step 9:

[0933] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking instructions. They complete the dish safely and deliciously, paying attention to all precautions.

[0934] ---

[0935] The above is a detailed explanation of the processing steps of this system.

[0936] (Example 1)

[0937] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0938] Conventional recipe suggestion systems have struggled to generate new recipes that are appropriate and timely in response to user input. Furthermore, the generated recipes sometimes lacked comprehensive ingredient lists, cooking instructions, and important notes, making them difficult for users to use.

[0939] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0940] In this invention, the server includes means for inputting conditions desired by the user, means for transmitting the input conditions to the server, means for the server to parse the received conditions in JSON format and input the parsed data into a generation AI model, means for generating a new cooking recipe based on the conditions using the generation AI model, and means for transmitting the generated recipe to a terminal and displaying the recipe on the terminal. This makes it possible to quickly generate a new cooking recipe based on the conditions desired by the user and provide a recipe that includes a detailed list of ingredients, cooking procedures, and precautions.

[0941] "Means for users to input desired conditions" refers to methods and devices for users to input cooking-related conditions on an interface.

[0942] "Means for sending entered conditions to the server" means a method and device for sending entered conditions from a terminal to a server using a communication protocol (e.g., HTTP).

[0943] "Means for a server to parse the conditions it receives in JSON format and input the parsed data into a generating AI model" means a method and apparatus for a server to parse the conditions it receives in JSON format using a data analysis library and input the analysis results into a generating AI model.

[0944] "Means for generating new recipes based on conditions using a generative AI model" means a method and apparatus for generating new recipes that match user conditions using a generative AI model.

[0945] "Means for sending a generated recipe to a terminal and displaying the recipe on the terminal" means a method and apparatus for converting a generated recipe into JSON format, sending it from the server to the terminal, and displaying it on the terminal in a format that is easy for the user to view.

[0946] "Means for converting and analyzing conditions in JSON format for input into a generated AI model by the server" means a method and apparatus for converting raw data received by the server into JSON format and analyzing those conditions.

[0947] "The generated recipe includes a list of ingredients, cooking instructions, and notes" means that the recipe output by the generating AI model includes a specific list of ingredients, detailed cooking instructions, and notes to keep in mind while cooking.

[0948] Modes for carrying out the invention

[0949] This invention provides a system that allows users to easily receive suggestions for new cooking recipes, and its implementation involves the following steps.

[0950] First, users access this system using an internet-connected device (such as a PC, smartphone, or tablet). To access the system, users need a web browser (e.g., Chrome, Firefox) or a dedicated application. On this interface, users enter their desired ingredients, cooking time, type of dish, difficulty level, and other preferences. For example, if they want a simple chicken dish, they would enter the corresponding information.

[0951] When a user clicks the "Request Proposal" button, the device converts the entered conditions into JSON data and sends it to the server as an HTTP request. The communication protocol used at this time is HTTP.

[0952] The server receives this request and parses the conditions in JSON format using a data analysis library (e.g., FastAPI, Flask). The parsed data is then input into a generative AI model (e.g., GPT-3, BERT). The generative AI model generates a new recipe based on the received conditions. This generation process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[0953] The generated recipe is converted back to JSON format on the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays it to the user in an easy-to-understand format. Frontend libraries and frameworks such as JavaScript and React may be used at this stage.

[0954] For example, if a new dish called "Lemon Garlic Chicken Sauté" is proposed, the generated recipe would look like this:

[0955] material:

[0956] 300g chicken breast

[0957] 1 lemon

[0958] 2 cloves of garlic

[0959] 2 tablespoons olive oil

[0960] Salt and pepper to taste

[0961] Cooking instructions:

[0962] 1. Cut the chicken breast into bite-sized pieces.

[0963] 2. Grate the lemon zest and squeeze out the juice.

[0964] 3. Mince the garlic.

[0965] 4. Heat olive oil in a frying pan and sauté the garlic.

[0966] 5. Add the chicken and sauté until it has a nice golden brown color.

[0967] 6. Add the lemon juice and zest, and season with salt and pepper.

[0968] Points to note:

[0969] Be careful not to burn the garlic.

[0970] To prevent the lemon flavor from dissipating, do not overheat it.

[0971] The advantage of this system is that users can receive new recipe suggestions with just a few clicks, and the process is simple. Users can create new dishes simply by following the suggested ingredients and cooking instructions. In this way, the present invention makes it possible for even cooking beginners to easily expand their culinary repertoire.

[0972] Examples of prompt statements are as follows:

[0973] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[0974] By inputting this prompt into the AI ​​generation model, a recipe suitable for the given conditions is generated and provided to the user.

[0975] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0976] System program processing flow

[0977] Step 1:

[0978] The user enters their desired conditions. The user inputs the ingredients they want to use, cooking time, type of dish, difficulty level, etc., on the interface. For example, they might select "chicken," "under 30 minutes," "sauté," and "easy." This generates input data based on the user's desired conditions. This input data is saved in JSON format.

[0979] Input: Conditions entered by the user in the interface

[0980] Output: Input data in JSON format

[0981] Step 2:

[0982] The terminal sends the input data to the server. When the user clicks the "Request Proposal" button, the terminal converts the entered conditions into JSON format data and sends it to the server as an HTTP request.

[0983] Input: Input data in JSON format

[0984] Output: HTTP request sent to the server

[0985] Step 3:

[0986] The server analyzes the received conditions. The server analyzes the received JSON data using a data analysis library (e.g., FastAPI, Flask) and inputs the analyzed data into the generating AI model. Specific data analysis steps include schema validation and extraction of necessary items.

[0987] Input: HTTP request in JSON format

[0988] Output: Analyzed data (Example: {"Ingredients": "Chicken", "Cooking time": "Under 30 minutes", "Type of dish": "Sauté", "Difficulty": "Easy"})

[0989] Step 4:

[0990] A generative AI model generates a new recipe. The server inputs the analyzed data as prompts into the generative AI model (e.g., GPT-3). The generative AI model generates a new recipe based on the given conditions. This process includes generating an ingredient list, cooking instructions, and notes.

[0991] Input: Analyzed data

[0992] Output: Generated recipe (Example: {"Ingredients": {...}, "Cooking Instructions": [...], "Notes": [...]})

[0993] Step 5:

[0994] The server converts the generated recipe into JSON format and sends it to the terminal. The generated recipe is then converted back into JSON format within the server and sent to the terminal as an HTTP response. Conversion and validation take place during this process.

[0995] Input: Generated recipe

[0996] Output: HTTP response in JSON format

[0997] Step 6:

[0998] The device parses and displays the recipe. The device reads the received data using a JSON parsing library and displays the recipe to the user in an easy-to-understand format. This display may utilize front-end libraries such as JavaScript or React.

[0999] Input: HTTP response in JSON format

[1000] Output: Recipe display in a format viewable by the user.

[1001] Example prompt statements

[1002] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[1003] By inputting this prompt into the AI ​​generation model, a recipe suitable for the given conditions is generated and provided to the user.

[1004] (Application Example 1)

[1005] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1006] Conventional recipe suggestion systems only provide users with suggested recipes, leaving them responsible for purchasing and arranging for the delivery of ingredients. Furthermore, there was a lack of systems capable of adequately handling recipe generation based on specific conditions. Additionally, there was insufficient means to efficiently procure the necessary ingredients when generating new recipes.

[1007] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1008] In this invention, the server includes means for inputting desired conditions from the user, means for transmitting the input conditions to the server, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions received by the server, means for ordering the necessary ingredients through a delivery service based on the generated recipe, and means for providing the generated recipe to the user. As a result, the user can not only be offered cooking recipes based on their desired conditions, but also have the delivery of the necessary ingredients for those recipes arranged all at once.

[1009] "A means for users to input their desired conditions" refers to a component that provides an interface where users can input conditions such as the ingredients they want to use, cooking time, type of dish, and difficulty level.

[1010] "Means for sending entered conditions to the server" refers to a data communication function for sending conditions entered by the user to the server via the network.

[1011] "A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server" refers to a function in which the server analyzes the user's conditions and generates new cooking recipes using a generative AI model based on those conditions.

[1012] "A means of ordering necessary ingredients through a delivery service based on a generated recipe" refers to a function that automatically orders the necessary ingredients through an online delivery service based on the ingredient list described in the generated recipe.

[1013] "Means of providing generated recipes to users" refers to a function for displaying or providing generated new cooking recipes to the user's device.

[1014] This invention is a system that proposes new recipes based on the user's desired conditions and allows the user to order the necessary ingredients through a delivery service based on those recipes. This system is configured as follows:

[1015] First, users access the system using a dedicated smartphone application. On the interface, users can input their desired conditions (for example, ingredients to use, cooking time, type of dish, difficulty level, etc.). This allows users to input specific instructions such as "a simple dish using chicken."

[1016] The entered conditions are converted into JSON data and sent to the server as an HTTP request. This communication is implemented using, for example, a frontend built with React Native and a backend using Node.js and Express.

[1017] The server receives the request and analyzes the data. The analyzed data is then input as a prompt to the generative AI based on OpenAI's GPT-4 model. An example of a prompt is: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes."

[1018] Generative AI generates new recipes based on the conditions it receives. This generation process includes algorithms to consider ingredients that meet the conditions, cooking procedures, and points to note. For example, if a new dish called "Chicken Stir-fry with Butter and Soy Sauce" is proposed, the generated recipe will include the following details:

[1019] material:

[1020] 200g chicken breast

[1021] 30g butter

[1022] 2 tablespoons soy sauce

[1023] 1 clove of garlic

[1024] Salt and pepper to taste

[1025] Cooking instructions:

[1026] 1. Cut the chicken breast into bite-sized pieces.

[1027] 2. Mince the garlic.

[1028] 3. Melt the butter in a frying pan and sauté the garlic.

[1029] 4. Add the chicken and stir-fry until it is nicely browned.

[1030] 5. Add soy sauce and adjust the taste.

[1031] Points to note:

[1032] Be careful not to burn the garlic.

[1033] After adding the soy sauce, adjust the temperature so that it doesn't get too hot.

[1034] The generated recipe is converted back into JSON format and sent to the user's terminal as an HTTP response. The user's terminal parses the received data and displays the recipe in a visually easy-to-understand format.

[1035] Furthermore, the system includes a function to automatically order the necessary ingredients from online delivery services based on the generated recipe. This allows users to order the necessary ingredients through a delivery service immediately after reviewing the recipe. Through this process, users can easily be presented with new recipes and simultaneously procure the necessary ingredients to prepare them.

[1036] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1037] Step 1:

[1038] The user enters their desired conditions using a smartphone application. This information includes the ingredients to be used, cooking time, type of dish, and difficulty level. For example, they might enter "a simple chicken dish that can be made in under 20 minutes." These conditions are converted into JSON data by the device.

[1039] Step 2:

[1040] The terminal sends the entered JSON data to the server as an HTTP request. The server receives this request and parses its contents. Specifically, the server's HTTP request processing functions, provided by Node.js and Express, are used.

[1041] Step 3:

[1042] The server analyzes the conditions and inputs them as a prompt to the generative AI. The prompt takes the following form: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes." After the prompt is generated, it is sent to the OpenAI GPT-4 model.

[1043] Step 4:

[1044] A generative AI (GPT-4 model) generates a new cooking recipe based on the prompt. This generation process includes ingredients that meet the specified criteria, cooking steps, and notes. The generated recipe is returned to the server. At this point, the output is specific recipe information.

[1045] Step 5:

[1046] The server converts the received recipe information into JSON format and sends it to the user's terminal as an HTTP response. Here, the input is the recipe information received from the generative AI, and the output is the response data returned to the user's terminal.

[1047] Step 6:

[1048] The device parses the received JSON data and displays it to the user in a visually easy-to-understand format. Specifically, the recipe's ingredient list, cooking instructions, and notes are displayed on a React Native interface. The user device's specific actions are parsing and displaying the received data.

[1049] Step 7:

[1050] The system automatically transmits data on the necessary ingredients to a delivery service based on the generated recipe. This process uses the ingredient list provided in the recipe to issue an order to the online delivery service's API. This eliminates the need for users to manually place orders, allowing the system to automatically procure the necessary ingredients.

[1051] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1052] ---

[1053] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[1054] First, the user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. After entering the conditions, the user collects emotional data through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators.

[1055] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the system. When the user enters the conditions and clicks the "Request Suggestions" button, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc.

[1056] The device sends the converted JSON data to the server as an HTTP request. The server receives this request and parses the data. During the parsing process, the server analyzes emotional data to understand the user's current emotional state. Based on this analyzed data, the server combines generative AI and an emotion engine to generate a new recipe.

[1057] The server inputs analyzed conditions and emotional data into the generative AI. Based on the received prompts, the generative AI generates a new recipe, providing one that is appropriate for the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[1058] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[1059] material:

[1060] 300g chicken breast

[1061] 1 lemon

[1062] 2 cloves of garlic

[1063] 2 tablespoons olive oil

[1064] Salt and pepper to taste

[1065] Cooking instructions:

[1066] 1. Cut the chicken breast into bite-sized pieces.

[1067] 2. Grate the lemon zest and squeeze out the juice.

[1068] 3. Mince the garlic.

[1069] 4. Heat olive oil in a frying pan and sauté the garlic.

[1070] 5. Add the chicken and sauté until it has a nice golden brown color.

[1071] 6. Add the lemon juice and zest, and season with salt and pepper.

[1072] Points to note:

[1073] Be careful not to burn the garlic.

[1074] To prevent the lemon flavor from dissipating, do not overheat it.

[1075] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[1076] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1077] This system allows users to receive new recipe suggestions with just a few clicks, and implementing them is easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. This system makes it easy for even beginner cooks to expand their culinary repertoire and improves the overall cooking experience.

[1078] ---

[1079] The following describes the processing flow.

[1080] ---

[1081] Step 1:

[1082] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, they might enter information such as "chicken," "easy," and "grilled."

[1083] Step 2:

[1084] After the user enters the necessary information, emotional data is collected through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators. For example, relaxed facial expressions and cheerful voice tones are collected.

[1085] Step 3:

[1086] The user reviews their input and clicks the "Request Proposal" button. The device then converts the user's entered conditions and collected sentiment data into JSON format. This data includes the entered ingredients, cooking methods, difficulty level, and sentiment index.

[1087] Step 4:

[1088] The device sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill", "Emotion": "Relax"}.

[1089] Step 5:

[1090] The server receives HTTP requests from the terminal and analyzes the data. Based on the analyzed data, the server utilizes an emotion engine to understand the user's emotional state. The emotion engine analyzes the user's emotional data and, for example, determines that "the user is relaxed."

[1091] Step 6:

[1092] Based on the analysis results from the emotion engine, the server inputs conditions and emotion data to the generative AI. For example, the prompt "A simple grilled chicken dish in a relaxed state" is sent to the generative AI.

[1093] Step 7:

[1094] Generative AI generates new cooking recipes based on the prompts it receives. This process includes algorithms to combine ingredients, cooking steps, and precautions that meet the given conditions. For example, it might generate a recipe for "Lemon Garlic Chicken Sauté."

[1095] The generative AI generates the following recipe:

[1096] material:

[1097] 300g chicken breast

[1098] 1 lemon

[1099] 2 cloves of garlic

[1100] 2 tablespoons olive oil

[1101] Salt and pepper to taste

[1102] Cooking instructions:

[1103] 1. Cut the chicken breast into bite-sized pieces.

[1104] 2. Grate the lemon zest and squeeze out the juice.

[1105] 3. Mince the garlic.

[1106] 4. Heat olive oil in a frying pan and sauté the garlic.

[1107] 5. Add the chicken and sauté until it has a nice golden brown color.

[1108] 6. Add the lemon juice and zest, and season with salt and pepper.

[1109] Points to note:

[1110] Be careful not to burn the garlic.

[1111] To prevent the lemon flavor from dissipating, do not overheat it.

[1112] Step 8:

[1113] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. For example, data such as {"Ingredients": [{"Chicken breast": "300g"}, {"Lemon": "1"}, {"Garlic": "2 cloves"}, {"Olive oil": "2 tablespoons"}, {"Salt": "to taste"}, {"Pepper": "to taste"}], "Cooking Instructions": ["Cut the chicken breast into bite-sized pieces.", "Grate the lemon zest and squeeze the juice.", ...], "Notes": ["Be careful not to burn the garlic.", "Do not overheat so that the lemon flavor does not dissipate."]} is sent.

[1114] Step 9:

[1115] The terminal analyzes recipe data received from the server and displays it on the user interface. This allows the user to check the ingredient list, cooking instructions, and important notes. Supplementary information and adjustments based on sentiment data are also displayed.

[1116] Step 10:

[1117] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1118] ---

[1119] The above is a description of the specific processing steps of the invention that combines an emotion engine.

[1120] (Example 2)

[1121] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1122] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in a problem where they cannot provide suggestions suitable for the user's current mood or condition. Furthermore, they offer a low degree of personalization, failing to improve the user experience.

[1123] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data, means for converting the conditions and emotional data into JSON format, means for transmitting the converted data to the server via communication, means for analyzing the data received by the server, means for generating a recipe using a generation AI model based on the analyzed data, and means for displaying the generated recipe on the user interface. This makes it possible to suggest highly personalized recipes that take into account the user's emotional state.

[1124] "Means for users to input their desired conditions" refers to interfaces or input devices for users to input conditions such as desired ingredients, cooking methods, difficulty level, and cooking time.

[1125] "Means of collecting user emotional data" refers to devices such as cameras and microphones used to collect emotional indicators such as the user's facial expressions and voice tone.

[1126] "Means for converting condition and sentiment data into JSON format" refers to software algorithms or programs for converting user-entered conditions and collected sentiment data into JSON format data.

[1127] "Means of sending converted data to a server via communication" refers to communication modules or protocols used to send converted JSON data to a server via a communication network such as the internet.

[1128] "Means for analyzing data received by the server" refers to software algorithms and analysis programs that analyze conditional data and emotional data received by the server to understand the user's desired characteristics and emotional state.

[1129] "Means of generating recipes using a generative AI model based on analyzed data" refers to software algorithms or generation programs that send prompts to a generative AI model based on analyzed data to generate new recipes.

[1130] "Means for displaying generated recipes on a user interface" refers to display devices or applications that display generated recipes on a user interface so that users can view them.

[1131] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[1132] The user first launches a browser or dedicated application to access the interface. The user then enters their desired ingredients, cooking method, difficulty level, cooking time, and other criteria. This input is done using an input device such as a keyboard or touchscreen.

[1133] Next, the user collects emotional data through a dedicated camera and microphone. This data can be collected using a webcam, a smartphone's built-in camera, or a microphone. This captures emotional indicators such as the user's facial expressions and voice tone in real time.

[1134] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the interface. When the user enters the conditions and clicks the "Request Suggestions" button, the device converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, cooking time, and sentiment indicators.

[1135] The terminal sends the converted JSON data to the server as an HTTP request. This transmission uses an internet-based communication module and the HTTP protocol. The server receives this request and parses the data.

[1136] The server uses analysis algorithms and emotion recognition engines to analyze the received data. During the analysis process, the server analyzes emotion data to understand the user's current emotional state. Then, based on the analyzed data, it uses a generative AI model to generate new recipes.

[1137] The server inputs analyzed conditions and emotional data into the generative AI model. Based on the received prompts, the generative AI model generates a new recipe, providing a recipe that suits the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[1138] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. The generative AI model will generate a recipe like this:

[1139] material:

[1140] 300g chicken breast

[1141] 1 lemon

[1142] 2 cloves of garlic

[1143] 2 tablespoons olive oil

[1144] Salt and pepper to taste

[1145] Cooking instructions:

[1146] 1. Cut the chicken breast into bite-sized pieces.

[1147] 2. Grate the lemon zest and squeeze out the juice.

[1148] 3. Mince the garlic.

[1149] 4. Heat olive oil in a frying pan and sauté the garlic.

[1150] 5. Add the chicken and sauté until it has a nice golden brown color.

[1151] 6. Add the lemon juice and zest, and season with salt and pepper.

[1152] Points to note:

[1153] Be careful not to burn the garlic.

[1154] To prevent the lemon flavor from dissipating, do not overheat it.

[1155] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[1156] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1157] An example of a prompt statement is as follows:

[1158] "Please suggest some simple chicken recipes. The user is relaxed."

[1159] In this way, the system allows users to receive new recipe suggestions with just a few clicks, and implementing them is extremely easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized recipe suggestions. This makes it easy for even novice cooks to expand their culinary repertoire and improves their overall cooking experience.

[1160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1161] Step 1:

[1162] The user launches a browser or dedicated application and accesses the interface. The user enters their desired conditions, such as ingredients (e.g., chicken), cooking method (e.g., grilling), difficulty level (e.g., easy), and cooking time (e.g., within 30 minutes). The entered conditions are saved on the device.

[1163] input:

[1164] Ingredients, cooking method, difficulty level, cooking time

[1165] output:

[1166] Data including user conditions (e.g., Ingredients: Chicken, Cooking method: Grilling, Difficulty: Easy, Cooking time: 30 minutes or less)

[1167] Specific actions:

[1168] Enter the conditions into the interface.

[1169] Click the "Request a recipe" button.

[1170] Step 2:

[1171] Users collect emotional data through a dedicated camera and microphone. The camera captures the user's facial expressions, and the microphone records the tone of their voice. This data is sent to an emotion analysis engine.

[1172] input:

[1173] User facial expressions and voice data

[1174] output:

[1175] Emotional analysis data (e.g., Relaxation)

[1176] Specific actions:

[1177] She smiles at the camera.

[1178] He speaks into the microphone in a gentle voice.

[1179] Step 3:

[1180] The device converts the user-inputted conditions and collected sentiment data into JSON format. This conversion is performed using a dedicated software algorithm.

[1181] input:

[1182] Ingredients, cooking method, difficulty level, cooking time, sentiment analysis data

[1183] output:

[1184] Data in JSON format (Example: {"Ingredients": "Chicken", "Cooking Method": "Grill", "Difficulty": "Easy", "Cooking Time": "Under 30 minutes", "Emotion": "Relaxed"})

[1185] Specific actions:

[1186] The software retrieves the input conditions and sentiment data from the terminal and converts them into JSON format.

[1187] Step 4:

[1188] The terminal sends the converted JSON data to the server as an HTTP request. HTTP is used as the communication protocol.

[1189] input:

[1190] Data in JSON format

[1191] output:

[1192] HTTP request sent to the server

[1193] Specific actions:

[1194] The device sends data to the server via the internet.

[1195] Step 5:

[1196] The server receives an HTTP request and parses the transmitted data. This parsing uses a sentiment analysis engine and data analysis algorithms.

[1197] input:

[1198] JSON data of the received HTTP request

[1199] output:

[1200] Analyzed user conditions and sentiment data

[1201] Specific actions:

[1202] The server executes a program to analyze the data it receives.

[1203] Step 6:

[1204] The server generates recipes using a generative AI model based on the analyzed data. The generative AI model receives a prompt such as: "Please suggest a simple chicken recipe. The user's mood is relaxed." The generative AI model then generates a new recipe.

[1205] input:

[1206] Analyzed condition and sentiment data

[1207] output:

[1208] Generated recipe data

[1209] Specific actions:

[1210] A prompt message is sent to the generative AI model to retrieve a new recipe.

[1211] Step 7:

[1212] The server converts the generated recipe data into JSON format and sends it to the terminal as an HTTP response.

[1213] input:

[1214] Recipe data

[1215] output:

[1216] Recipe data in JSON format

[1217] Specific actions:

[1218] The server converts the generated recipe into JSON format and sends it as an HTTP response.

[1219] Step 8:

[1220] The terminal parses the JSON-formatted recipe data received from the server and displays it on the user interface. Users can check the ingredient list, cooking instructions, and important notes.

[1221] input:

[1222] Recipe data in JSON format

[1223] output:

[1224] Visually displayed recipe information

[1225] Specific actions:

[1226] The device analyzes the recipe data and displays it on the screen.

[1227] Step 9:

[1228] The user begins cooking based on the provided recipe. During cooking, the emotion engine monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1229] input:

[1230] Real-time sentiment data

[1231] output:

[1232] Real-time suggestions and advice

[1233] Specific actions:

[1234] Users provide emotional data through the camera and microphone, and the device provides corresponding feedback.

[1235] (Application Example 2)

[1236] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1237] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in recipes that are not suitable for the user's mood or stress level. Furthermore, it was difficult to instantly suggest recipes that matched the user's mood or purchasing intent for the day. This led to dissatisfaction with the suggested recipes, making it difficult for users to continue using the system.

[1238] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data through a dedicated camera and microphone, means including an emotion engine for analyzing the collected emotional data, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions and emotional data received by the server, and means for providing the generated recipe to the user. This makes it possible to suggest personalized recipes based on the user's emotional state, thereby improving user satisfaction and continued use of the system.

[1239] "Means for users to input desired conditions" refers to providing an interface for users to input conditions such as the ingredients, cooking method, difficulty level, and cooking time for the dishes they want.

[1240] "Means for sending entered conditions to the server" refers to means that have the function of converting conditions entered by the user into digital data and sending that data to the server via the network.

[1241] "Methods for collecting user emotional data through dedicated cameras and microphones" refers to methods of collecting emotional indicators such as the user's facial expressions and voice tone using cameras and microphones, and storing them as digital data.

[1242] "Means including an emotion engine for analyzing collected emotion data" refers to means including algorithms and software for analyzing emotion data collected by a dedicated camera or microphone and determining the user's emotional state.

[1243] "A method for generating recipes using generative AI to generate new cooking recipes" refers to a method of creating new cooking recipes using a generative AI model based on input conditions and sentiment data.

[1244] "Means of providing generated recipes to users" refers to means of displaying recipes generated by generative AI on the user interface.

[1245] "Means for the server to analyze conditional and emotional data for input into a generative AI" refers to methods for analyzing received conditional and emotional data and converting it into a format that the generative AI can understand.

[1246] "List of ingredients, cooking instructions, and notes" refers to information that includes a list of ingredients needed to make the dish, specific cooking steps, and points to keep in mind during cooking.

[1247] This invention is a system that suggests new dishes based on conditions desired by the user, and by combining it with an emotion engine, it achieves more accurate recipe suggestions.

[1248] First, the user launches a dedicated application using a communication terminal. Accessing the application's interface, the user inputs conditions such as desired ingredients, cooking method, difficulty level, and cooking time.

[1249] Next, the user collects emotional data through a dedicated camera and microphone. This collects emotional indicators such as the user's facial expressions and voice tone. This data is analyzed by an emotion engine to determine the user's current emotional state.

[1250] After the conditions are entered, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc. The converted data is sent to the server as an HTTP request.

[1251] The server analyzes the received data and generates prompts for input to the generative AI based on the conditions and sentiment data. Examples of prompts include: "Please suggest recipes using chicken," "Please suggest simple dishes with short cooking times," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[1252] Generative AI generates new cooking recipes based on received prompt text. This process includes algorithms and sentiment data-based complementation to combine ingredients, cooking procedures, and precautions that meet the given conditions.

[1253] The generated recipe includes an ingredient list, cooking instructions, and notes, and is converted to JSON format by the server. The server sends this data to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface.

[1254] Users can view the generated recipe through their device and cook according to the provided ingredient list, cooking instructions, and precautions. Furthermore, an emotion engine monitors the user's emotional state in real time during cooking and can offer suggestions and advice as needed.

[1255] This system allows users to receive new recipe suggestions in just a few clicks, and making them easy to implement. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. Even beginners can easily expand their culinary horizons, making this a system that enhances the overall cooking experience.

[1256] The hardware used includes smartphone and PC cameras. The software used includes OpenCV (image processing library), EmotionAnalyzer (emotion analysis library), requests (HTTP request library), and JSON (data exchange format).

[1257] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1258] Step 1:

[1259] The user launches a dedicated application using a communication terminal and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. The entered conditions are temporarily stored on the terminal. Specific inputs include "chicken," "easy," and "under 30 minutes."

[1260] Step 2:

[1261] The user collects emotional data through a dedicated camera and microphone. This emotional data captures the user's facial expressions and voice tone in real time and transmits it to the device. Specifically, the camera photographs the user's face, and the voice input device records the user's voice.

[1262] Step 3:

[1263] The device analyzes the collected emotional data using EmotionAnalyzer. The analysis results in the user's current emotional state (e.g., "relaxed"). This emotional state data is also stored on the device.

[1264] Step 4:

[1265] The terminal converts the entered conditions and emotion data into JSON format. This data includes ingredients, cooking method, difficulty level, and emotion state. The generated JSON data is sent to the server as an HTTP request.

[1266] Step 5:

[1267] The server receives an HTTP request and parses the JSON data. It extracts conditional and sentiment data and generates prompts to input into the generative AI based on them. Examples of specific prompts include: "Please suggest a recipe using chicken," "Please suggest a simple dish with a short cooking time," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[1268] Step 6:

[1269] The server inputs prompts into the generative AI, which then generates a new recipe. This process involves algorithms that combine ingredients, cooking steps, and precautions that meet the specified criteria, along with calculations to supplement emotional data. The generated recipe includes an ingredient list, cooking steps, and precautions.

[1270] Step 7:

[1271] The server converts the generated recipe into JSON format and sends it to the terminal as an HTTP response. The terminal receives the response from the server and parses the data.

[1272] Step 8:

[1273] The device displays the analyzed recipe data in a user interface. Users can view the provided ingredient list, cooking instructions, and precautions. The user interface may also display real-time advice and suggestions to help during cooking.

[1274] Step 9:

[1275] The user begins cooking based on the provided recipe. During cooking, an emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed. This allows the user to proceed with cooking with peace of mind.

[1276] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1277] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1278] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1279] [Fourth Embodiment]

[1280] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1281] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1282] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1283] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1284] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1285] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1286] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1287] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1288] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1289] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1290] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1291] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1292] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1293] ---

[1294] This invention is a system that allows users to easily receive suggestions for new cooking recipes, and its implementation follows the steps below.

[1295] First, users access the system using a browser or a dedicated application. Users can enter their desired conditions on the interface. These conditions include the ingredients to be used, cooking time, type of dish, and difficulty level. For example, if a user wants a "simple chicken dish," they would enter the corresponding information. Once the user enters the conditions and clicks the "Request Suggestions" button, the terminal sends the entered conditions to the server.

[1296] The terminal converts the user's input into JSON data and sends it to the server as an HTTP request. The server receives this request and parses the data. Based on this parsed data, the server inputs conditions into a generative AI. The generative AI generates a new recipe based on the received conditions. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[1297] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[1298] material:

[1299] 300g chicken breast

[1300] 1 lemon

[1301] 2 cloves of garlic

[1302] 2 tablespoons olive oil

[1303] Salt and pepper to taste

[1304] Cooking instructions:

[1305] 1. Cut the chicken breast into bite-sized pieces.

[1306] 2. Grate the lemon zest and squeeze out the juice.

[1307] 3. Mince the garlic.

[1308] 4. Heat olive oil in a frying pan and sauté the garlic.

[1309] 5. Add the chicken and sauté until it has a nice golden brown color.

[1310] 6. Add the lemon juice and zest, and season with salt and pepper.

[1311] Points to note:

[1312] Be careful not to burn the garlic.

[1313] To prevent the lemon flavor from dissipating, do not overheat it.

[1314] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays the recipe to the user in an easy-to-read format. This allows the user to start cooking based on the suggested recipe.

[1315] This system allows users to receive new recipe suggestions with just a few clicks, and making them is easy. Users can create new dishes simply by following the provided ingredients and cooking instructions. In this way, the present invention provides a system that allows even cooking beginners to easily expand their culinary repertoire.

[1316] ---

[1317] The following describes the processing flow.

[1318] ---

[1319] Step 1:

[1320] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, if the user wants a "simple chicken dish," they would enter information such as "chicken," "simple," and "grilled."

[1321] Step 2:

[1322] The user enters the conditions and clicks the "Request Proposal" button. The device then converts the user's entered conditions into JSON data. This data includes the entered ingredients, cooking method, difficulty level, etc.

[1323] Step 3:

[1324] The terminal sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill"}.

[1325] Step 4:

[1326] The server receives HTTP requests from terminals and parses the data. Based on the parsed data, the server creates prompts to generate new cooking recipes. These prompts are then input into a generative AI.

[1327] Step 5:

[1328] The server inputs prompts to the generative AI. Based on the received prompts, the generative AI generates a new recipe. This process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the specified criteria.

[1329] Step 6:

[1330] Generative AI generates recipes based on given conditions. For example, it might generate a dish called "Lemon Garlic Chicken Sauté." This recipe includes the following information:

[1331] material:

[1332] 300g chicken breast

[1333] 1 lemon

[1334] 2 cloves of garlic

[1335] 2 tablespoons olive oil

[1336] Salt and pepper to taste

[1337] Cooking instructions:

[1338] 1. Cut the chicken breast into bite-sized pieces.

[1339] 2. Grate the lemon zest and squeeze out the juice.

[1340] 3. Mince the garlic.

[1341] 4. Heat olive oil in a frying pan and sauté the garlic.

[1342] 5. Add the chicken and sauté until it has a nice golden brown color.

[1343] 6. Add the lemon juice and zest, and season with salt and pepper.

[1344] Points to note:

[1345] Be careful not to burn the garlic.

[1346] To prevent the lemon flavor from dissipating, do not overheat it.

[1347] Step 7:

[1348] The server converts the generated recipe into JSON data and sends it to the terminal as an HTTP response.

[1349] Step 8:

[1350] The terminal analyzes the recipe data received from the server and displays it on the user interface. This allows the user to check the ingredient list, cooking instructions, and important notes.

[1351] Step 9:

[1352] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking instructions. They complete the dish safely and deliciously, paying attention to all precautions.

[1353] ---

[1354] The above is a detailed explanation of the processing steps of this system.

[1355] (Example 1)

[1356] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1357] Conventional recipe suggestion systems have struggled to generate new recipes that are appropriate and timely in response to user input. Furthermore, the generated recipes sometimes lacked comprehensive ingredient lists, cooking instructions, and important notes, making them difficult for users to use.

[1358] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1359] In this invention, the server includes means for inputting conditions desired by the user, means for transmitting the input conditions to the server, means for the server to parse the received conditions in JSON format and input the parsed data into a generation AI model, means for generating a new cooking recipe based on the conditions using the generation AI model, and means for transmitting the generated recipe to a terminal and displaying the recipe on the terminal. This makes it possible to quickly generate a new cooking recipe based on the conditions desired by the user and provide a recipe that includes a detailed list of ingredients, cooking procedures, and precautions.

[1360] "Means for users to input desired conditions" refers to methods and devices for users to input cooking-related conditions on an interface.

[1361] "Means for sending entered conditions to the server" means a method and device for sending entered conditions from a terminal to a server using a communication protocol (e.g., HTTP).

[1362] "Means for a server to parse the conditions it receives in JSON format and input the parsed data into a generating AI model" means a method and apparatus for a server to parse the conditions it receives in JSON format using a data analysis library and input the analysis results into a generating AI model.

[1363] "Means for generating new recipes based on conditions using a generative AI model" means a method and apparatus for generating new recipes that match user conditions using a generative AI model.

[1364] "Means for sending a generated recipe to a terminal and displaying the recipe on the terminal" means a method and apparatus for converting a generated recipe into JSON format, sending it from the server to the terminal, and displaying it on the terminal in a format that is easy for the user to view.

[1365] "Means for converting and analyzing conditions in JSON format for input into a generated AI model by the server" means a method and apparatus for converting raw data received by the server into JSON format and analyzing those conditions.

[1366] "The generated recipe includes a list of ingredients, cooking instructions, and notes" means that the recipe output by the generating AI model includes a specific list of ingredients, detailed cooking instructions, and notes to keep in mind while cooking.

[1367] Modes for carrying out the invention

[1368] This invention provides a system that allows users to easily receive suggestions for new cooking recipes, and its implementation involves the following steps.

[1369] First, users access this system using an internet-connected device (such as a PC, smartphone, or tablet). To access the system, users need a web browser (e.g., Chrome, Firefox) or a dedicated application. On this interface, users enter their desired ingredients, cooking time, type of dish, difficulty level, and other preferences. For example, if they want a simple chicken dish, they would enter the corresponding information.

[1370] When a user clicks the "Request Proposal" button, the device converts the entered conditions into JSON data and sends it to the server as an HTTP request. The communication protocol used at this time is HTTP.

[1371] The server receives this request and parses the conditions in JSON format using a data analysis library (e.g., FastAPI, Flask). The parsed data is then input into a generative AI model (e.g., GPT-3, BERT). The generative AI model generates a new recipe based on the received conditions. This generation process includes an algorithm to combine ingredients, cooking steps, and precautions that meet the conditions.

[1372] The generated recipe is converted back to JSON format on the server and sent to the terminal as an HTTP response. The terminal parses the received data and displays it to the user in an easy-to-understand format. Frontend libraries and frameworks such as JavaScript and React may be used at this stage.

[1373] For example, if a new dish called "Lemon Garlic Chicken Sauté" is proposed, the generated recipe would look like this:

[1374] material:

[1375] 300g chicken breast

[1376] 1 lemon

[1377] 2 cloves of garlic

[1378] 2 tablespoons olive oil

[1379] Salt and pepper to taste

[1380] Cooking instructions:

[1381] 1. Cut the chicken breast into bite-sized pieces.

[1382] 2. Grate the lemon zest and squeeze out the juice.

[1383] 3. Mince the garlic.

[1384] 4. Heat olive oil in a frying pan and sauté the garlic.

[1385] 5. Add the chicken and sauté until it has a nice golden brown color.

[1386] 6. Add the lemon juice and zest, and season with salt and pepper.

[1387] Points to note:

[1388] Be careful not to burn the garlic.

[1389] To prevent the lemon flavor from dissipating, do not overheat it.

[1390] The advantage of this system is that users can receive new recipe suggestions with just a few clicks, and the process is simple. Users can create new dishes simply by following the suggested ingredients and cooking instructions. In this way, the present invention makes it possible for even cooking beginners to easily expand their culinary repertoire.

[1391] Examples of prompt statements are as follows:

[1392] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[1393] By inputting this prompt into the AI ​​generation model, a recipe suitable for the given conditions is generated and provided to the user.

[1394] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1395] System program processing flow

[1396] Step 1:

[1397] The user enters their desired conditions. The user inputs the ingredients they want to use, cooking time, type of dish, difficulty level, etc., on the interface. For example, they might select "chicken," "under 30 minutes," "sauté," and "easy." This generates input data based on the user's desired conditions. This input data is saved in JSON format.

[1398] Input: Conditions entered by the user in the interface

[1399] Output: Input data in JSON format

[1400] Step 2:

[1401] The terminal sends the input data to the server. When the user clicks the "Request Proposal" button, the terminal converts the entered conditions into JSON format data and sends it to the server as an HTTP request.

[1402] Input: Input data in JSON format

[1403] Output: HTTP request sent to the server

[1404] Step 3:

[1405] The server analyzes the received conditions. The server analyzes the received JSON data using a data analysis library (e.g., FastAPI, Flask) and inputs the analyzed data into the generating AI model. Specific data analysis steps include schema validation and extraction of necessary items.

[1406] Input: HTTP request in JSON format

[1407] Output: Analyzed data (Example: {"Ingredients": "Chicken", "Cooking time": "Under 30 minutes", "Type of dish": "Sauté", "Difficulty": "Easy"})

[1408] Step 4:

[1409] A generative AI model generates a new recipe. The server inputs the analyzed data as prompts into the generative AI model (e.g., GPT-3). The generative AI model generates a new recipe based on the given conditions. This process includes generating an ingredient list, cooking instructions, and notes.

[1410] Input: Analyzed data

[1411] Output: Generated recipe (Example: {"Ingredients": {...}, "Cooking Instructions": [...], "Notes": [...]})

[1412] Step 5:

[1413] The server converts the generated recipe into JSON format and sends it to the terminal. The generated recipe is then converted back into JSON format within the server and sent to the terminal as an HTTP response. Conversion and validation take place during this process.

[1414] Input: Generated recipe

[1415] Output: HTTP response in JSON format

[1416] Step 6:

[1417] The device parses and displays the recipe. The device reads the received data using a JSON parsing library and displays the recipe to the user in an easy-to-understand format. This display may utilize front-end libraries such as JavaScript or React.

[1418] Input: HTTP response in JSON format

[1419] Output: Recipe display in a format viewable by the user.

[1420] Example prompt statements

[1421] "Please suggest a simple chicken recipe. The cooking time should be under 30 minutes, and the ingredients should be common."

[1422] By inputting this prompt into the AI ​​generation model, a recipe suitable for the given conditions is generated and provided to the user.

[1423] (Application Example 1)

[1424] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1425] Conventional recipe suggestion systems only provide users with suggested recipes, leaving them responsible for purchasing and arranging for the delivery of ingredients. Furthermore, there was a lack of systems capable of adequately handling recipe generation based on specific conditions. Additionally, there was insufficient means to efficiently procure the necessary ingredients when generating new recipes.

[1426] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1427] In this invention, the server includes means for inputting desired conditions from the user, means for transmitting the input conditions to the server, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions received by the server, means for ordering the necessary ingredients through a delivery service based on the generated recipe, and means for providing the generated recipe to the user. As a result, the user can not only be offered cooking recipes based on their desired conditions, but also have the delivery of the necessary ingredients for those recipes arranged all at once.

[1428] "A means for users to input their desired conditions" refers to a component that provides an interface where users can input conditions such as the ingredients they want to use, cooking time, type of dish, and difficulty level.

[1429] "Means for sending entered conditions to the server" refers to a data communication function for sending conditions entered by the user to the server via the network.

[1430] "A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server" refers to a function in which the server analyzes the user's conditions and generates new cooking recipes using a generative AI model based on those conditions.

[1431] "A means of ordering necessary ingredients through a delivery service based on a generated recipe" refers to a function that automatically orders the necessary ingredients through an online delivery service based on the ingredient list described in the generated recipe.

[1432] "Means of providing generated recipes to users" refers to a function for displaying or providing generated new cooking recipes to the user's device.

[1433] This invention is a system that proposes new recipes based on the user's desired conditions and allows the user to order the necessary ingredients through a delivery service based on those recipes. This system is configured as follows:

[1434] First, users access the system using a dedicated smartphone application. On the interface, users can input their desired conditions (for example, ingredients to use, cooking time, type of dish, difficulty level, etc.). This allows users to input specific instructions such as "a simple dish using chicken."

[1435] The entered conditions are converted into JSON data and sent to the server as an HTTP request. This communication is implemented using, for example, a frontend built with React Native and a backend using Node.js and Express.

[1436] The server receives the request and analyzes the data. The analyzed data is then input as a prompt to the generative AI based on OpenAI's GPT-4 model. An example of a prompt is: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes."

[1437] Generative AI generates new recipes based on the conditions it receives. This generation process includes algorithms to consider ingredients that meet the conditions, cooking procedures, and points to note. For example, if a new dish called "Chicken Stir-fry with Butter and Soy Sauce" is proposed, the generated recipe will include the following details:

[1438] material:

[1439] 200g chicken breast

[1440] 30g butter

[1441] 2 tablespoons soy sauce

[1442] 1 clove of garlic

[1443] Salt and pepper to taste

[1444] Cooking instructions:

[1445] 1. Cut the chicken breast into bite-sized pieces.

[1446] 2. Mince the garlic.

[1447] 3. Melt the butter in a frying pan and sauté the garlic.

[1448] 4. Add the chicken and stir-fry until it is nicely browned.

[1449] 5. Add soy sauce and adjust the taste.

[1450] Points to note:

[1451] Be careful not to burn the garlic.

[1452] After adding the soy sauce, adjust the temperature so that it doesn't get too hot.

[1453] The generated recipe is converted back into JSON format and sent to the user's terminal as an HTTP response. The user's terminal parses the received data and displays the recipe in a visually easy-to-understand format.

[1454] Furthermore, the system includes a function to automatically order the necessary ingredients from online delivery services based on the generated recipe. This allows users to order the necessary ingredients through a delivery service immediately after reviewing the recipe. Through this process, users can easily be presented with new recipes and simultaneously procure the necessary ingredients to prepare them.

[1455] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1456] Step 1:

[1457] The user enters their desired conditions using a smartphone application. This information includes the ingredients to be used, cooking time, type of dish, and difficulty level. For example, they might enter "a simple chicken dish that can be made in under 20 minutes." These conditions are converted into JSON data by the device.

[1458] Step 2:

[1459] The terminal sends the entered JSON data to the server as an HTTP request. The server receives this request and parses its contents. Specifically, the server's HTTP request processing functions, provided by Node.js and Express, are used.

[1460] Step 3:

[1461] The server analyzes the conditions and inputs them as a prompt to the generative AI. The prompt takes the following form: "Create a new recipe based on the following conditions: A simple chicken dish in under 20 minutes." After the prompt is generated, it is sent to the OpenAI GPT-4 model.

[1462] Step 4:

[1463] A generative AI (GPT-4 model) generates a new cooking recipe based on the prompt. This generation process includes ingredients that meet the specified criteria, cooking steps, and notes. The generated recipe is returned to the server. At this point, the output is specific recipe information.

[1464] Step 5:

[1465] The server converts the received recipe information into JSON format and sends it to the user's terminal as an HTTP response. Here, the input is the recipe information received from the generative AI, and the output is the response data returned to the user's terminal.

[1466] Step 6:

[1467] The device parses the received JSON data and displays it to the user in a visually easy-to-understand format. Specifically, the recipe's ingredient list, cooking instructions, and notes are displayed on a React Native interface. The user device's specific actions are parsing and displaying the received data.

[1468] Step 7:

[1469] The system automatically transmits data on the necessary ingredients to a delivery service based on the generated recipe. This process uses the ingredient list provided in the recipe to issue an order to the online delivery service's API. This eliminates the need for users to manually place orders, allowing the system to automatically procure the necessary ingredients.

[1470] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1471] ---

[1472] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[1473] First, the user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. After entering the conditions, the user collects emotional data through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators.

[1474] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the system. When the user enters the conditions and clicks the "Request Suggestions" button, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc.

[1475] The device sends the converted JSON data to the server as an HTTP request. The server receives this request and parses the data. During the parsing process, the server analyzes emotional data to understand the user's current emotional state. Based on this analyzed data, the server combines generative AI and an emotion engine to generate a new recipe.

[1476] The server inputs analyzed conditions and emotional data into the generative AI. Based on the received prompts, the generative AI generates a new recipe, providing one that is appropriate for the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[1477] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. A generative AI would generate the following recipe.

[1478] material:

[1479] 300g chicken breast

[1480] 1 lemon

[1481] 2 cloves of garlic

[1482] 2 tablespoons olive oil

[1483] Salt and pepper to taste

[1484] Cooking instructions:

[1485] 1. Cut the chicken breast into bite-sized pieces.

[1486] 2. Grate the lemon zest and squeeze out the juice.

[1487] 3. Mince the garlic.

[1488] 4. Heat olive oil in a frying pan and sauté the garlic.

[1489] 5. Add the chicken and sauté until it has a nice golden brown color.

[1490] 6. Add the lemon juice and zest, and season with salt and pepper.

[1491] Points to note:

[1492] Be careful not to burn the garlic.

[1493] To prevent the lemon flavor from dissipating, do not overheat it.

[1494] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[1495] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1496] This system allows users to receive new recipe suggestions with just a few clicks, and implementing them is easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. This system makes it easy for even beginner cooks to expand their culinary repertoire and improves the overall cooking experience.

[1497] ---

[1498] The following describes the processing flow.

[1499] ---

[1500] Step 1:

[1501] The user launches a browser or dedicated application and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. For example, they might enter information such as "chicken," "easy," and "grilled."

[1502] Step 2:

[1503] After the user enters the necessary information, emotional data is collected through a dedicated camera and microphone. This data includes the user's facial expressions, voice tone, and other emotional indicators. For example, relaxed facial expressions and cheerful voice tones are collected.

[1504] Step 3:

[1505] The user reviews their input and clicks the "Request Proposal" button. The device then converts the user's entered conditions and collected sentiment data into JSON format. This data includes the entered ingredients, cooking methods, difficulty level, and sentiment index.

[1506] Step 4:

[1507] The device sends the converted JSON data to the server as an HTTP request. For example, the following data is sent to the server: {"Ingredients": "Chicken", "Difficulty": "Easy", "Cooking Method": "Grill", "Emotion": "Relax"}.

[1508] Step 5:

[1509] The server receives HTTP requests from the terminal and analyzes the data. Based on the analyzed data, the server utilizes an emotion engine to understand the user's emotional state. The emotion engine analyzes the user's emotional data and, for example, determines that "the user is relaxed."

[1510] Step 6:

[1511] Based on the analysis results from the emotion engine, the server inputs conditions and emotion data to the generative AI. For example, the prompt "A simple grilled chicken dish in a relaxed state" is sent to the generative AI.

[1512] Step 7:

[1513] Generative AI generates new cooking recipes based on the prompts it receives. This process includes algorithms to combine ingredients, cooking steps, and precautions that meet the given conditions. For example, it might generate a recipe for "Lemon Garlic Chicken Sauté."

[1514] The generative AI generates the following recipe:

[1515] material:

[1516] 300g chicken breast

[1517] 1 lemon

[1518] 2 cloves of garlic

[1519] 2 tablespoons olive oil

[1520] Salt and pepper to taste

[1521] Cooking instructions:

[1522] 1. Cut the chicken breast into bite-sized pieces.

[1523] 2. Grate the lemon zest and squeeze out the juice.

[1524] 3. Mince the garlic.

[1525] 4. Heat olive oil in a frying pan and sauté the garlic.

[1526] 5. Add the chicken and sauté until it has a nice golden brown color.

[1527] 6. Add the lemon juice and zest, and season with salt and pepper.

[1528] Points to note:

[1529] Be careful not to burn the garlic.

[1530] To prevent the lemon flavor from dissipating, do not overheat it.

[1531] Step 8:

[1532] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. For example, data such as {"Ingredients": [{"Chicken breast": "300g"}, {"Lemon": "1"}, {"Garlic": "2 cloves"}, {"Olive oil": "2 tablespoons"}, {"Salt": "to taste"}, {"Pepper": "to taste"}], "Cooking Instructions": ["Cut the chicken breast into bite-sized pieces.", "Grate the lemon zest and squeeze the juice.", ...], "Notes": ["Be careful not to burn the garlic.", "Do not overheat so that the lemon flavor does not dissipate."]} is sent.

[1533] Step 9:

[1534] The terminal analyzes recipe data received from the server and displays it on the user interface. This allows the user to check the ingredient list, cooking instructions, and important notes. Supplementary information and adjustments based on sentiment data are also displayed.

[1535] Step 10:

[1536] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1537] ---

[1538] The above is a description of the specific processing steps of the invention that combines an emotion engine.

[1539] (Example 2)

[1540] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1541] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in a problem where they cannot provide suggestions suitable for the user's current mood or condition. Furthermore, they offer a low degree of personalization, failing to improve the user experience.

[1542] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data, means for converting the conditions and emotional data into JSON format, means for transmitting the converted data to the server via communication, means for analyzing the data received by the server, means for generating a recipe using a generation AI model based on the analyzed data, and means for displaying the generated recipe on the user interface. This makes it possible to suggest highly personalized recipes that take into account the user's emotional state.

[1543] "Means for users to input their desired conditions" refers to interfaces or input devices for users to input conditions such as desired ingredients, cooking methods, difficulty level, and cooking time.

[1544] "Means of collecting user emotional data" refers to devices such as cameras and microphones used to collect emotional indicators such as the user's facial expressions and voice tone.

[1545] "Means for converting condition and sentiment data into JSON format" refers to software algorithms or programs for converting user-entered conditions and collected sentiment data into JSON format data.

[1546] "Means of sending converted data to a server via communication" refers to communication modules or protocols used to send converted JSON data to a server via a communication network such as the internet.

[1547] "Means for analyzing data received by the server" refers to software algorithms and analysis programs that analyze conditional data and emotional data received by the server to understand the user's desired characteristics and emotional state.

[1548] "Means of generating recipes using a generative AI model based on analyzed data" refers to software algorithms or generation programs that send prompts to a generative AI model based on analyzed data to generate new recipes.

[1549] "Means for displaying generated recipes on a user interface" refers to display devices or applications that display generated recipes on a user interface so that users can view them.

[1550] This invention is a system that proposes new dishes based on conditions desired by the user, and further achieves more accurate recipe suggestions by combining it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is shown below.

[1551] The user first launches a browser or dedicated application to access the interface. The user then enters their desired ingredients, cooking method, difficulty level, cooking time, and other criteria. This input is done using an input device such as a keyboard or touchscreen.

[1552] Next, the user collects emotional data through a dedicated camera and microphone. This data can be collected using a webcam, a smartphone's built-in camera, or a microphone. This captures emotional indicators such as the user's facial expressions and voice tone in real time.

[1553] For example, if a user requests a "simple chicken dish" and has a relaxed expression, this information is entered into the interface. When the user enters the conditions and clicks the "Request Suggestions" button, the device converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, cooking time, and sentiment indicators.

[1554] The terminal sends the converted JSON data to the server as an HTTP request. This transmission uses an internet-based communication module and the HTTP protocol. The server receives this request and parses the data.

[1555] The server uses analysis algorithms and emotion recognition engines to analyze the received data. During the analysis process, the server analyzes emotion data to understand the user's current emotional state. Then, based on the analyzed data, it uses a generative AI model to generate new recipes.

[1556] The server inputs analyzed conditions and emotional data into the generative AI model. Based on the received prompts, the generative AI model generates a new recipe, providing a recipe that suits the user's emotional state. This process includes algorithms and emotional data-based complementation to combine ingredients, cooking procedures, and precautions that meet the conditions.

[1557] As a concrete example, consider a case where a new dish, "Lemon Garlic Chicken Sauté," is proposed. The generative AI model will generate a recipe like this:

[1558] material:

[1559] 300g chicken breast

[1560] 1 lemon

[1561] 2 cloves of garlic

[1562] 2 tablespoons olive oil

[1563] Salt and pepper to taste

[1564] Cooking instructions:

[1565] 1. Cut the chicken breast into bite-sized pieces.

[1566] 2. Grate the lemon zest and squeeze out the juice.

[1567] 3. Mince the garlic.

[1568] 4. Heat olive oil in a frying pan and sauté the garlic.

[1569] 5. Add the chicken and sauté until it has a nice golden brown color.

[1570] 6. Add the lemon juice and zest, and season with salt and pepper.

[1571] Points to note:

[1572] Be careful not to burn the garlic.

[1573] To prevent the lemon flavor from dissipating, do not overheat it.

[1574] The generated recipe is converted to JSON format by the server and sent to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface. This allows the user to check the list of ingredients, cooking instructions, and precautions. Supplementary information and adjustments based on sentiment data are also displayed.

[1575] The user begins cooking based on the provided recipe. The user gathers the ingredients and follows the cooking procedure. Paying attention to precautions, the user completes the dish safely and deliciously. Throughout this process, the emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1576] An example of a prompt statement is as follows:

[1577] "Please suggest some simple chicken recipes. The user is relaxed."

[1578] In this way, the system allows users to receive new recipe suggestions with just a few clicks, and implementing them is extremely easy. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized recipe suggestions. This makes it easy for even novice cooks to expand their culinary repertoire and improves their overall cooking experience.

[1579] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1580] Step 1:

[1581] The user launches a browser or dedicated application and accesses the interface. The user enters their desired conditions, such as ingredients (e.g., chicken), cooking method (e.g., grilling), difficulty level (e.g., easy), and cooking time (e.g., within 30 minutes). The entered conditions are saved on the device.

[1582] input:

[1583] Ingredients, cooking method, difficulty level, cooking time

[1584] output:

[1585] Data including user conditions (e.g., Ingredients: Chicken, Cooking method: Grilling, Difficulty: Easy, Cooking time: 30 minutes or less)

[1586] Specific actions:

[1587] Enter the conditions into the interface.

[1588] Click the "Request a recipe" button.

[1589] Step 2:

[1590] Users collect emotional data through a dedicated camera and microphone. The camera captures the user's facial expressions, and the microphone records the tone of their voice. This data is sent to an emotion analysis engine.

[1591] input:

[1592] User facial expressions and voice data

[1593] output:

[1594] Emotional analysis data (e.g., Relaxation)

[1595] Specific actions:

[1596] She smiles at the camera.

[1597] He speaks into the microphone in a gentle voice.

[1598] Step 3:

[1599] The device converts the user-inputted conditions and collected sentiment data into JSON format. This conversion is performed using a dedicated software algorithm.

[1600] input:

[1601] Ingredients, cooking method, difficulty level, cooking time, sentiment analysis data

[1602] output:

[1603] Data in JSON format (Example: {"Ingredients": "Chicken", "Cooking Method": "Grill", "Difficulty": "Easy", "Cooking Time": "Under 30 minutes", "Emotion": "Relaxed"})

[1604] Specific actions:

[1605] The software retrieves the input conditions and sentiment data from the terminal and converts them into JSON format.

[1606] Step 4:

[1607] The terminal sends the converted JSON data to the server as an HTTP request. HTTP is used as the communication protocol.

[1608] input:

[1609] Data in JSON format

[1610] output:

[1611] HTTP request sent to the server

[1612] Specific actions:

[1613] The device sends data to the server via the internet.

[1614] Step 5:

[1615] The server receives an HTTP request and parses the transmitted data. This parsing uses a sentiment analysis engine and data analysis algorithms.

[1616] input:

[1617] JSON data of the received HTTP request

[1618] output:

[1619] Analyzed user conditions and sentiment data

[1620] Specific actions:

[1621] The server executes a program to analyze the data it receives.

[1622] Step 6:

[1623] The server generates recipes using a generative AI model based on the analyzed data. The generative AI model receives a prompt such as: "Please suggest a simple chicken recipe. The user's mood is relaxed." The generative AI model then generates a new recipe.

[1624] input:

[1625] Analyzed condition and sentiment data

[1626] output:

[1627] Generated recipe data

[1628] Specific actions:

[1629] A prompt message is sent to the generative AI model to retrieve a new recipe.

[1630] Step 7:

[1631] The server converts the generated recipe data into JSON format and sends it to the terminal as an HTTP response.

[1632] input:

[1633] Recipe data

[1634] output:

[1635] Recipe data in JSON format

[1636] Specific actions:

[1637] The server converts the generated recipe into JSON format and sends it as an HTTP response.

[1638] Step 8:

[1639] The terminal parses the JSON-formatted recipe data received from the server and displays it on the user interface. Users can check the ingredient list, cooking instructions, and important notes.

[1640] input:

[1641] Recipe data in JSON format

[1642] output:

[1643] Visually displayed recipe information

[1644] Specific actions:

[1645] The device analyzes the recipe data and displays it on the screen.

[1646] Step 9:

[1647] The user begins cooking based on the provided recipe. During cooking, the emotion engine monitors the user's emotional state and provides real-time suggestions and advice as needed.

[1648] input:

[1649] Real-time sentiment data

[1650] output:

[1651] Real-time suggestions and advice

[1652] Specific actions:

[1653] Users provide emotional data through the camera and microphone, and the device provides corresponding feedback.

[1654] (Application Example 2)

[1655] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1656] Conventional recipe suggestion systems generate recipes without considering the user's emotional state, resulting in recipes that are not suitable for the user's mood or stress level. Furthermore, it was difficult to instantly suggest recipes that matched the user's mood or purchasing intent for the day. This led to dissatisfaction with the suggested recipes, making it difficult for users to continue using the system.

[1657] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting conditions desired by the user, means for collecting the user's emotional data through a dedicated camera and microphone, means including an emotion engine for analyzing the collected emotional data, means for generating a recipe using a generative AI for generating new cooking recipes based on the conditions and emotional data received by the server, and means for providing the generated recipe to the user. This makes it possible to suggest personalized recipes based on the user's emotional state, thereby improving user satisfaction and continued use of the system.

[1658] "Means for users to input desired conditions" refers to providing an interface for users to input conditions such as the ingredients, cooking method, difficulty level, and cooking time for the dishes they want.

[1659] "Means for sending entered conditions to the server" refers to means that have the function of converting conditions entered by the user into digital data and sending that data to the server via the network.

[1660] "Methods for collecting user emotional data through dedicated cameras and microphones" refers to methods of collecting emotional indicators such as the user's facial expressions and voice tone using cameras and microphones, and storing them as digital data.

[1661] "Means including an emotion engine for analyzing collected emotion data" refers to means including algorithms and software for analyzing emotion data collected by a dedicated camera or microphone and determining the user's emotional state.

[1662] "A method for generating recipes using generative AI to generate new cooking recipes" refers to a method of creating new cooking recipes using a generative AI model based on input conditions and sentiment data.

[1663] "Means of providing generated recipes to users" refers to means of displaying recipes generated by generative AI on the user interface.

[1664] "Means for the server to analyze conditional and emotional data for input into a generative AI" refers to methods for analyzing received conditional and emotional data and converting it into a format that the generative AI can understand.

[1665] "List of ingredients, cooking instructions, and notes" refers to information that includes a list of ingredients needed to make the dish, specific cooking steps, and points to keep in mind during cooking.

[1666] This invention is a system that suggests new dishes based on conditions desired by the user, and by combining it with an emotion engine, it achieves more accurate recipe suggestions.

[1667] First, the user launches a dedicated application using a communication terminal. Accessing the application's interface, the user inputs conditions such as desired ingredients, cooking method, difficulty level, and cooking time.

[1668] Next, the user collects emotional data through a dedicated camera and microphone. This collects emotional indicators such as the user's facial expressions and voice tone. This data is analyzed by an emotion engine to determine the user's current emotional state.

[1669] After the conditions are entered, the terminal converts the entered conditions and sentiment data into JSON format. This data includes the entered ingredients, cooking method, difficulty level, sentiment index, etc. The converted data is sent to the server as an HTTP request.

[1670] The server analyzes the received data and generates prompts for input to the generative AI based on the conditions and sentiment data. Examples of prompts include: "Please suggest recipes using chicken," "Please suggest simple dishes with short cooking times," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[1671] Generative AI generates new cooking recipes based on received prompt text. This process includes algorithms and sentiment data-based complementation to combine ingredients, cooking procedures, and precautions that meet the given conditions.

[1672] The generated recipe includes an ingredient list, cooking instructions, and notes, and is converted to JSON format by the server. The server sends this data to the terminal as an HTTP response. The terminal parses the recipe data received from the server and displays it in the user interface.

[1673] Users can view the generated recipe through their device and cook according to the provided ingredient list, cooking instructions, and precautions. Furthermore, an emotion engine monitors the user's emotional state in real time during cooking and can offer suggestions and advice as needed.

[1674] This system allows users to receive new recipe suggestions in just a few clicks, and making them easy to implement. Furthermore, recipes are supplemented based on the user's emotions, enabling more personalized cooking suggestions. Even beginners can easily expand their culinary horizons, making this a system that enhances the overall cooking experience.

[1675] The hardware used includes smartphone and PC cameras. The software used includes OpenCV (image processing library), EmotionAnalyzer (emotion analysis library), requests (HTTP request library), and JSON (data exchange format).

[1676] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1677] Step 1:

[1678] The user launches a dedicated application using a communication terminal and accesses the interface. The user enters conditions such as desired ingredients, cooking method, difficulty level, and cooking time. The entered conditions are temporarily stored on the terminal. Specific inputs include "chicken," "easy," and "under 30 minutes."

[1679] Step 2:

[1680] The user collects emotional data through a dedicated camera and microphone. This emotional data captures the user's facial expressions and voice tone in real time and transmits it to the device. Specifically, the camera photographs the user's face, and the voice input device records the user's voice.

[1681] Step 3:

[1682] The device analyzes the collected emotional data using EmotionAnalyzer. The analysis results in the user's current emotional state (e.g., "relaxed"). This emotional state data is also stored on the device.

[1683] Step 4:

[1684] The terminal converts the entered conditions and emotion data into JSON format. This data includes ingredients, cooking method, difficulty level, and emotion state. The generated JSON data is sent to the server as an HTTP request.

[1685] Step 5:

[1686] The server receives an HTTP request and parses the JSON data. It extracts conditional and sentiment data and generates prompts to input into the generative AI based on them. Examples of specific prompts include: "Please suggest a recipe using chicken," "Please suggest a simple dish with a short cooking time," and "I'm feeling relaxed, so I'd like a dish that will help me relax."

[1687] Step 6:

[1688] The server inputs prompts into the generative AI, which then generates a new recipe. This process involves algorithms that combine ingredients, cooking steps, and precautions that meet the specified criteria, along with calculations to supplement emotional data. The generated recipe includes an ingredient list, cooking steps, and precautions.

[1689] Step 7:

[1690] The server converts the generated recipe into JSON format and sends it to the terminal as an HTTP response. The terminal receives the response from the server and parses the data.

[1691] Step 8:

[1692] The device displays the analyzed recipe data in a user interface. Users can view the provided ingredient list, cooking instructions, and precautions. The user interface may also display real-time advice and suggestions to help during cooking.

[1693] Step 9:

[1694] The user begins cooking based on the provided recipe. During cooking, an emotion engine continuously monitors the user's emotional state and provides real-time suggestions and advice as needed. This allows the user to proceed with cooking with peace of mind.

[1695] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1696] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1697] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1698] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1699] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1700] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1701] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1702] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1703] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1704] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1705] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1706] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1707] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1708] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1709] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1710] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1711] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1712] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1713] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1714] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1715] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1716] The following is further disclosed regarding the embodiments described above.

[1717] (Claim 1)

[1718] A means for the user to input their desired conditions,

[1719] A means for sending the entered conditions to the server,

[1720] A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server,

[1721] A means of providing the generated recipe to the user,

[1722] A system that includes this.

[1723] (Claim 2)

[1724] The system according to claim 1, further comprising means for analyzing conditions for input to a generative AI from a server.

[1725] (Claim 3)

[1726] The system according to claim 1, wherein the generated recipe includes a list of ingredients, cooking instructions, and precautions.

[1727] "Example 1"

[1728] (Claim 1)

[1729] A means for the user to input their desired conditions,

[1730] A means for sending the entered conditions to the server,

[1731] A means of parsing the conditions received by the server in JSON format and inputting the parsed data into an AI model,

[1732] A means of generating new cooking recipes based on conditions using a generative AI model,

[1733] A means of sending the generated recipe to a terminal and displaying the recipe on the terminal,

[1734] A system that includes this.

[1735] (Claim 2)

[1736] The system according to claim 1, further comprising means for converting conditions into JSON format and analyzing them for input into the generated AI model by the server.

[1737] (Claim 3)

[1738] The system according to claim 1, wherein the generated recipe includes a list of ingredients, cooking instructions, and precautions.

[1739] "Application Example 1"

[1740] (Claim 1)

[1741] A means for the user to input their desired conditions,

[1742] A means for sending the entered conditions to the server,

[1743] A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server,

[1744] A means of ordering the necessary ingredients through a delivery service based on the generated recipe,

[1745] A means of providing the generated recipe to the user,

[1746] A system that includes this.

[1747] (Claim 2)

[1748] The system according to claim 1, further comprising means for analyzing conditions for input to a generative AI from a server.

[1749] (Claim 3)

[1750] The system according to claim 1, wherein the generated recipe not only includes a list of ingredients, cooking instructions, and precautions, but also includes means for generating a list of necessary ingredients based on the recipe generated by the generative AI and linking it to a delivery service.

[1751] "Example 2 of combining an emotion engine"

[1752] (Claim 1)

[1753] A means for the user to input their desired conditions,

[1754] Means for collecting user sentiment data,

[1755] A means of converting condition and sentiment data into JSON format,

[1756] A means of sending the converted data to a server via communication,

[1757] A means of analyzing the data received by the server,

[1758] A means of generating recipes using a generative AI model based on analytical data,

[1759] A means of displaying the generated recipe in the user interface,

[1760] A system that includes this.

[1761] (Claim 2)

[1762] The system according to claim 1, further comprising means for analyzing conditional and sentiment data received by the server for input into a generated AI model.

[1763] (Claim 3)

[1764] The system according to claim 1, wherein the generated recipe includes a list of ingredients, cooking instructions, and precautions.

[1765] "Application example 2 when combining with an emotional engine"

[1766] (Claim 1)

[1767] A means for the user to input their desired conditions,

[1768] A means for sending the entered conditions to the server,

[1769] A means of collecting user emotional data through dedicated cameras and microphones,

[1770] A means including an emotion engine for analyzing collected emotion data,

[1771] A method for generating recipes using a generative AI that generates new cooking recipes based on conditions and emotional data received by the server,

[1772] A means of providing the generated recipe to the user,

[1773] A system that includes this.

[1774] (Claim 2)

[1775] The system according to claim 1, further comprising means for analyzing conditional and emotional data for input to a generative AI.

[1776] (Claim 3)

[1777] The system according to claim 1, wherein the generated recipe includes a list of ingredients, cooking instructions, and precautions. [Explanation of Symbols]

[1778] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the user to input their desired conditions, A means for sending the entered conditions to the server, A method for generating recipes using a generative AI to generate new cooking recipes based on conditions received by the server, A means of providing the generated recipe to the user, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing conditions for input to a generative AI from a server.

3. The system according to claim 1, wherein the generated recipe includes a list of ingredients, cooking instructions, and precautions.

Images